import mne
import numpy as np
import scipy
from scipy.signal import savgol_filter
from scipy.stats import trim_mean
from sklearn.manifold import MDS, TSNE
from sklearn.cluster import KMeans
from sklearn.covariance import shrunk_covariance
import copy

import torch
import seaborn as sns
import matplotlib.pyplot as plt
from matplotlib.pyplot import MultipleLocator
from pylab import mpl
import seaborn as sns
import dill

import warnings
warnings.filterwarnings('ignore')

from utils import UDEC_Network, draw_states, ttest_for_clusters

plt.rcParams['font.family']=['Arial', 'Times New Roman']
plt.style.use('default')
mpl.rcParams["axes.unicode_minus"] = False
%config InlineBackend.figure_format = 'svg'

font = {'family':['Arial', 'Times New Roman'], 'color':'k', 'weight':'normal', 'size':10 }
colors = sns.color_palette('tab10')

device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
print(device)

mne.cuda.init_cuda(verbose=True)

cuda:0
Now using CUDA device 0
Enabling CUDA with 10.09 GB available memory

subject_num = 40
erp_data = np.zeros((subject_num, 2, 28, 256)) # [subject, type, ch, time]

trim = lambda x: trim_mean(x, 0.3, axis=0)

file_path_pre = './N170_Data/'
file_path_post = '_N170_shifted_ds_reref_ucbip_hpfilt_ica_corr_cbip_elist_bins_epoch_interp_ar.set'

for sub in range(subject_num):
    file_name = file_path_pre + str(sub+1) + file_path_post
    # from -200 ms to 800 ms, baseline correction performed
    epo = mne.io.read_epochs_eeglab(file_name);
    
    # epo.ch_names
    eog_ch_list = ['HEOG_left', 'HEOG_right', 'VEOG_lower', '(corr) HEOG',
                    '(corr) VEOG', '(uncorr) HEOG', '(uncorr) VEOG']
    epo.drop_channels(eog_ch_list);

    reject = dict(eeg=80e-6 )      # unit: V (EEG channels)
    flat_criteria = dict(eeg=1e-6)
    epo.drop_bad(reject, flat=flat_criteria);
    # epo.plot_drop_log();
    # epo.plot(events=True);

    events_dict = { }
    for pic in ['face', 'car']:
        events_dict[pic] = []

    for id in epo.event_id:
        # bin 1 Faces
        # bin 2 Cars
        # bin 3 Scrambled Faces
        # bin 4 Scrambled Cars
        if id[1] == '1':
            events_dict['face'].append(id)
        elif id[1] == '2':
            events_dict['car'].append(id)
        
    for i, pic in enumerate(['face', 'car']):
        erp_data[sub, i] = epo[events_dict[pic]].average(method=trim).get_data()

Extracting parameters from e:\论文写作\论文2数据分析\N170\N170_Data\1_N170_shifted_ds_reref_ucbip_hpfilt_ica_corr_cbip_elist_bins_epoch_interp_ar.set...
Not setting metadata
240 matching events found
No baseline correction applied
0 projection items activated
Ready.
    Rejecting  epoch based on EEG : ['PO4']
    Rejecting  epoch based on EEG : ['P7']
    Rejecting  epoch based on EEG : ['PO4']
    Rejecting  epoch based on EEG : ['PO4']
    Rejecting  epoch based on EEG : ['P7', 'PO8']
    Rejecting  epoch based on EEG : ['PO7', 'PO3', 'PO4']
    Rejecting  epoch based on EEG : ['PO8']
    Rejecting  epoch based on EEG : ['FP1', 'PO7', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
    Rejecting  epoch based on EEG : ['FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['F7', 'PO3', 'Pz', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'FC4', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['F7', 'FC4']
    Rejecting  epoch based on EEG : ['F7', 'P7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4', 'C6', 'PO8', 'O2']
    Rejecting  epoch based on EEG : ['F7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
    Rejecting  epoch based on EEG : ['FC4']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['F7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'O1', 'Oz', 'F4', 'FC4', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'FC4']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4', 'C6', 'P8', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC3', 'C3', 'C5', 'P3', 'P7', 'PO7', 'PO3', 'O1', 'Oz', 'Pz', 'CPz', 'FP2', 'Fz', 'F4', 'F8', 'FC4', 'FCz', 'Cz', 'C4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['P7', 'PO7', 'O1', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['P7', 'PO7', 'O1', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['P7', 'PO7', 'O1', 'Oz', 'Pz', 'FC4', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['PO7', 'PO8']
    Rejecting  epoch based on EEG : ['PO7', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'FC4', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'F4', 'FC4', 'C6', 'P8', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'P7', 'PO7', 'F4', 'FC4', 'C6', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'F4', 'FC4', 'C4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'O1', 'FC4', 'C6', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'PO3', 'O1', 'Pz', 'FC4', 'C6', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'PO7', 'FC4', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC3', 'PO7', 'F4', 'FC4', 'PO8', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'O1', 'F4', 'FC4', 'C6', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'O1', 'F4', 'FC4', 'C4', 'C6', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'F4', 'FC4', 'C6', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4', 'C6', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'FC4', 'C6', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO3', 'Pz', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'PO3']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'PO3', 'FC4', 'P8', 'PO8', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'F4', 'FC4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['FP1', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'PO3', 'O1', 'F4', 'FC4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4', 'C6', 'P8', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'O1', 'F4', 'FC4', 'C6', 'P8', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'PO3', 'O1', 'F4', 'FC4', 'C6', 'P8', 'PO8', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'FC4', 'C6', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'FC4', 'C6', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'O1', 'F4', 'FC4', 'C4', 'C6', 'P4', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'FC3', 'P7', 'PO7', 'F4', 'FC4', 'P4', 'P8', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'O1', 'F4', 'FC4', 'C4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'PO3', 'O1', 'F4', 'FC4', 'C6', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'PO7', 'O1', 'F4', 'FC4', 'C6', 'P8', 'PO8', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'FC3', 'P7', 'PO7', 'F4', 'FC4', 'C6', 'P8', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'O1', 'F4', 'FC4', 'C4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'PO3', 'O1', 'Oz', 'FC4', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['Oz']
    Rejecting  epoch based on EEG : ['PO4']
    Rejecting  epoch based on EEG : ['PO3', 'O1']
    Rejecting  epoch based on EEG : ['Oz']
    Rejecting  epoch based on EEG : ['F7']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'Oz', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'Oz', 'F4', 'FC4']
    Rejecting  epoch based on EEG : ['F7', 'P7', 'PO7', 'PO3', 'O1', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'PO3', 'O1', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['P7', 'PO7', 'O1', 'P8', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'O1', 'FC4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'O1', 'F4', 'FC4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'O1', 'F4', 'FC4', 'C6', 'P8', 'PO8', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'F4', 'FC4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'FC3', 'C3', 'C5', 'P3', 'P7', 'PO7', 'PO3', 'O1', 'Oz', 'Pz', 'CPz', 'FP2', 'Fz', 'F4', 'F8', 'FC4', 'FCz', 'Cz', 'C4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'C5', 'P3', 'P7', 'PO7', 'PO3', 'O1', 'Oz', 'F4', 'FC4', 'C4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'PO3', 'O1', 'Oz', 'F4', 'FC4', 'C4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC3', 'C5', 'P7', 'PO7', 'PO3', 'O1', 'Oz', 'Pz', 'F4', 'FC4', 'C4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'PO3', 'O1', 'F4', 'FC4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'O1', 'F4', 'FC4', 'C4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'C5', 'P7', 'PO7', 'O1', 'F4', 'FC4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'C5', 'P7', 'PO7', 'PO3', 'O1', 'Pz', 'F4', 'FC4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'O1', 'F4', 'FC4', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'PO7', 'O1', 'F4', 'FC4', 'C4', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'C5', 'P7', 'PO7', 'FC4', 'P8', 'PO8', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'P8', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'PO7', 'PO3', 'O1', 'Oz', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'Oz', 'P4', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'PO3', 'PO8']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1', 'O1']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'O1', 'F4', 'FC4', 'PO8', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'PO3', 'O1', 'Oz', 'FC4', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4', 'C6']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4', 'C6', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'C5', 'FC4', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'C5', 'FC4', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC3', 'F4', 'FC4', 'C6', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'F4', 'FC4', 'C6', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4', 'C6']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4', 'C6']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'C5', 'F4', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'C5', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'FC4', 'C6']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'F4', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC3', 'FC4', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'C5', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'C5', 'Oz', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'C5', 'PO7', 'Oz', 'FC4', 'C6', 'P4', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'FC4', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC3', 'P7', 'PO7', 'O1', 'F4', 'FC4', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'C5', 'P7', 'PO7', 'F4', 'FC4', 'C6', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'FC4', 'P8', 'PO8']

C:\Users\Administrator\AppData\Local\Temp\ipykernel_6512\2407259580.py:12: RuntimeWarning: At least one epoch has multiple events. Only the latency of the first event will be retained.
  epo = mne.io.read_epochs_eeglab(file_name);

    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4', 'C6', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4', 'C6']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'FC3', 'C5', 'F4', 'FC4', 'PO8', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'P7', 'Oz']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'Oz']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'Oz']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'PO3', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'PO7', 'PO3', 'FC4', 'C6']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'FC3', 'PO7', 'F4', 'FC4', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'C5', 'F4', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4', 'C6']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'Oz', 'CPz']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['F7']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4', 'C6']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'Pz', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4', 'C6']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'F4', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'C5', 'FC4', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'FC3', 'F4', 'FC4', 'C6', 'P8', 'PO8', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC4']
192 bad epochs dropped
Extracting parameters from e:\论文写作\论文2数据分析\N170\N170_Data\2_N170_shifted_ds_reref_ucbip_hpfilt_ica_corr_cbip_elist_bins_epoch_interp_ar.set...
Not setting metadata
314 matching events found
No baseline correction applied
0 projection items activated
Ready.
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['PO3']
    Rejecting  epoch based on EEG : ['PO7']
    Rejecting  epoch based on EEG : ['PO7']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['PO7']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['PO3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['PO3']
    Rejecting  epoch based on EEG : ['P3', 'Pz', 'CPz']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['PO3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['Pz']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['Pz']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['PO3', 'Pz']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['PO3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['PO4']
    Rejecting  epoch based on EEG : ['Pz']
    Rejecting  epoch based on EEG : ['PO3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['FCz', 'Cz']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['PO3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['PO3']
    Rejecting  epoch based on EEG : ['PO3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['PO4']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['P3']
    Rejecting  epoch based on EEG : ['PO3']
    Rejecting  epoch based on EEG : ['P3']
70 bad epochs dropped

C:\Users\Administrator\AppData\Local\Temp\ipykernel_6512\2407259580.py:12: RuntimeWarning: At least one epoch has multiple events. Only the latency of the first event will be retained.
  epo = mne.io.read_epochs_eeglab(file_name);
C:\Users\Administrator\AppData\Local\Temp\ipykernel_6512\2407259580.py:12: RuntimeWarning: At least one epoch has multiple events. Only the latency of the first event will be retained.
  epo = mne.io.read_epochs_eeglab(file_name);

Extracting parameters from e:\论文写作\论文2数据分析\N170\N170_Data\3_N170_shifted_ds_reref_ucbip_hpfilt_ica_corr_cbip_elist_bins_epoch_interp_ar.set...
Not setting metadata
301 matching events found
No baseline correction applied
0 projection items activated
Ready.
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F3', 'FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2', 'FC4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F3', 'Pz', 'CPz', 'FP2', 'F4']
    Rejecting  epoch based on EEG : ['Oz', 'FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4', 'PO4']
    Rejecting  epoch based on EEG : ['Oz', 'FP2', 'F4', 'O2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['Oz', 'FP2', 'F4', 'O2']
    Rejecting  epoch based on EEG : ['F3', 'F7', 'PO3', 'O1', 'Pz', 'FP2', 'F4']
    Rejecting  epoch based on EEG : ['F7', 'FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['Oz', 'FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F7', 'FP2']
    Rejecting  epoch based on EEG : ['F3', 'FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['PO3', 'O1', 'Oz', 'FP2', 'PO8']
    Rejecting  epoch based on EEG : ['F3', 'Pz', 'FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F7', 'FP2', 'F4']
    Rejecting  epoch based on EEG : ['F3', 'F7', 'PO3', 'Pz', 'FP2', 'F4', 'PO4']
    Rejecting  epoch based on EEG : ['P3', 'PO7', 'PO3', 'Pz', 'CPz', 'FP2', 'F4', 'Cz', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['F7', 'FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F4']
    Rejecting  epoch based on EEG : ['F3', 'F7', 'FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'P3', 'P7', 'PO7', 'PO3', 'O1', 'Oz', 'Pz', 'CPz', 'FP2', 'F4', 'F8', 'FC4', 'C6', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['F3', 'FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'Oz', 'FP2']
    Rejecting  epoch based on EEG : ['F7', 'FP2']
    Rejecting  epoch based on EEG : ['P3', 'PO3', 'FP2', 'F4', 'F8', 'PO4']
    Rejecting  epoch based on EEG : ['PO3', 'FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F3', 'FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F3', 'FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['F3']
    Rejecting  epoch based on EEG : ['Oz', 'FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F3', 'FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'FP2']
    Rejecting  epoch based on EEG : ['F7', 'FP2']
    Rejecting  epoch based on EEG : ['F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'Pz', 'FP2']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'P3', 'P7', 'PO7', 'PO3', 'O1', 'Oz', 'Pz', 'FP2', 'F4', 'C4', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F7', 'P3', 'PO3', 'O1', 'Oz', 'Pz', 'CPz', 'FP2', 'F4', 'F8', 'P4', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['PO3', 'FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['Pz', 'FP2', 'F4', 'F8']
    Rejecting  epoch based on EEG : ['F3', 'PO3', 'Oz', 'FP2', 'F4', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F3', 'FP2', 'F4']
    Rejecting  epoch based on EEG : ['PO7', 'PO3', 'FP2', 'Fz', 'F4']
    Rejecting  epoch based on EEG : ['FP2', 'C6']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['O1', 'FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['PO3', 'FP2', 'P8', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'PO7', 'PO3', 'O1', 'Oz', 'Pz', 'FP2', 'F4', 'F8', 'P8', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP1', 'P3', 'PO7', 'PO3', 'O1', 'Oz', 'Pz', 'FP2', 'F4', 'F8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F3', 'Pz', 'FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F3', 'F7', 'FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F7', 'FP2', 'F4']
    Rejecting  epoch based on EEG : ['F3', 'F7', 'FP2']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['F7', 'FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F3', 'FP2', 'F4', 'FC4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F3', 'F7']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'P3', 'P7', 'PO7', 'PO3', 'O1', 'Oz', 'Pz', 'FP2', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'P3', 'P7', 'PO7', 'PO3', 'O1', 'Oz', 'Pz', 'CPz', 'FP2', 'Fz', 'F4', 'F8', 'P4', 'PO4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2', 'FC4']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F3', 'FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'PO3', 'O1', 'Oz', 'Pz', 'FP2', 'F4', 'FC4', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['F7', 'FP2']
    Rejecting  epoch based on EEG : ['P7', 'PO3', 'FP2', 'F4']
    Rejecting  epoch based on EEG : ['F3']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['PO7', 'FP2', 'P8', 'PO8', 'PO4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F3', 'P3', 'P7', 'PO7', 'PO3', 'FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['P3', 'PO7', 'Pz', 'FP2']
    Rejecting  epoch based on EEG : ['F3']
    Rejecting  epoch based on EEG : ['FC4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F3', 'FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['PO3', 'Oz', 'Pz', 'FP2', 'F4', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['F3']
    Rejecting  epoch based on EEG : ['FP1', 'O1', 'FP2', 'PO4']
    Rejecting  epoch based on EEG : ['F7', 'FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2', 'F4']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP2']
228 bad epochs dropped
Extracting parameters from e:\论文写作\论文2数据分析\N170\N170_Data\4_N170_shifted_ds_reref_ucbip_hpfilt_ica_corr_cbip_elist_bins_epoch_interp_ar.set...
Not setting metadata
292 matching events found
No baseline correction applied
0 projection items activated
Ready.
    Rejecting  epoch based on EEG : ['C5']
    Rejecting  epoch based on EEG : ['F7', 'PO7', 'F4']
    Rejecting  epoch based on EEG : ['PO7', 'F8', 'PO8']
    Rejecting  epoch based on EEG : ['F7', 'PO7', 'O1', 'FP2', 'F8', 'PO8']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FC3', 'C5', 'P7', 'PO7', 'PO3', 'O1', 'Oz', 'FP2', 'F4', 'F8', 'FC4', 'C4', 'C6', 'P8', 'PO8', 'O2']
    Rejecting  epoch based on EEG : ['F8']
    Rejecting  epoch based on EEG : ['F7']
    Rejecting  epoch based on EEG : ['F7']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'FC3', 'C3', 'C5', 'P3', 'P7', 'PO7', 'PO3', 'O1', 'Oz', 'FP2', 'Fz', 'F4', 'F8', 'FC4', 'FCz', 'Cz', 'C6', 'P4', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'FC3', 'C5', 'P3', 'P7', 'PO7', 'PO3', 'O1', 'Oz', 'FP2', 'Fz', 'F4', 'F8', 'P8', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['F7', 'PO7', 'O1', 'FP2']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'FP2', 'PO8', 'PO4', 'O2']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1', 'FP2']
    Rejecting  epoch based on EEG : ['F7']
    Rejecting  epoch based on EEG : ['F7']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'O1', 'FP2', 'F4', 'F8', 'FC4', 'C4', 'C6', 'PO8', 'O2']
    Rejecting  epoch based on EEG : ['F7', 'PO7', 'O1', 'F8', 'PO8']
    Rejecting  epoch based on EEG : ['F7', 'PO7', 'FP2', 'P8', 'PO8']
    Rejecting  epoch based on EEG : ['PO7', 'PO8']
    Rejecting  epoch based on EEG : ['F7', 'PO7']
    Rejecting  epoch based on EEG : ['F7']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'FC3', 'C5', 'PO7', 'O1', 'FP2', 'F4', 'P8', 'PO8', 'O2']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['F7']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'FC3', 'C3', 'C5', 'PO7', 'O1', 'FP2', 'F4', 'F8', 'FC4', 'C4', 'C6', 'P8', 'PO8', 'O2']
28 bad epochs dropped
Extracting parameters from e:\论文写作\论文2数据分析\N170\N170_Data\5_N170_shifted_ds_reref_ucbip_hpfilt_ica_corr_cbip_elist_bins_epoch_interp_ar.set...

C:\Users\Administrator\AppData\Local\Temp\ipykernel_6512\2407259580.py:12: RuntimeWarning: At least one epoch has multiple events. Only the latency of the first event will be retained.
  epo = mne.io.read_epochs_eeglab(file_name);
C:\Users\Administrator\AppData\Local\Temp\ipykernel_6512\2407259580.py:12: RuntimeWarning: At least one epoch has multiple events. Only the latency of the first event will be retained.
  epo = mne.io.read_epochs_eeglab(file_name);

Not setting metadata
318 matching events found
No baseline correction applied
0 projection items activated
Ready.
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['F4']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1', 'F4']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['P8']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['Oz']
    Rejecting  epoch based on EEG : ['F7', 'Oz', 'F8', 'O2']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1', 'F3', 'F7', 'FC3', 'C5', 'F8', 'FC4', 'C4', 'C6']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['FP1', 'F7']
    Rejecting  epoch based on EEG : ['FP1']
    Rejecting  epoch based on EEG : ['C6']
24 bad epochs dropped
Extracting parameters from e:\论文写作\论文2数据分析\N170\N170_Data\6_N170_shifted_ds_reref_ucbip_hpfilt_ica_corr_cbip_elist_bins_epoch_interp_ar.set...
Not setting metadata
238 matching events found
No baseline correction applied
0 projection items activated
Ready.
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP1', 'PO7', 'FP2']
    Rejecting  epoch based on EEG : ['FC4']
    Rejecting  epoch based on EEG : ['FP1', 'FP2']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['PO7', 'FP2']
    Rejecting  epoch based on EEG : ['O1']
    Rejecting  epoch based on EEG : ['FP2']
    Rejecting  epoch based on EEG : ['FP1', 'F7', 'FP2', 'F4', 'F8', 'FC4', 'C4', 'C6']
    Rejecting  epoch based on EEG : ['FP1', 'F4', 'F8', 'FC4']
10 bad epochs dropped
Extracting parameters from e:\论文写作\论文2数据分析\N170\N170_Data\7_N170_shifted_ds_reref_ucbip_hpfilt_ica_corr_cbip_elist_bins_epoch_interp_ar.set...
Not setting metadata
307 matching events found

C:\Users\Administrator\AppData\Local\Temp\ipykernel_6512\2407259580.py:12: RuntimeWarning: At least one epoch has multiple events. Only the latency of the first event will be retained.
  epo = mne.io.read_epochs_eeglab(file_name);
C:\Users\Administrator\AppData\Local\Temp\ipykernel_6512\2407259580.py:12: RuntimeWarning: At least one epoch has multiple events. Only the latency of the first event will be retained.
  epo = mne.io.read_epochs_eeglab(file_name);

No baseline correction applied
0 projection items activated
Ready.
    Rejecting  epoch based on EEG : ['F3']
    Rejecting  epoch based on EEG : ['C6']
    Rejecting  epoch based on EEG : ['C6']
    Rejecting  epoch based on EEG : ['C6']
    Rejecting  epoch based on EEG : ['C6']
    Rejecting  epoch based on EEG : ['PO7']
    Rejecting  epoch based on EEG : ['O1']
    Rejecting  epoch based on EEG : ['O1']
    Rejecting  epoch based on EEG : ['O1']
9 bad epochs dropped
Extracting parameters from e:\论文写作\论文2数据分析\N170\N170_Data\8_N170_shifted_ds_reref_ucbip_hpfilt_ica_corr_cbip_elist_bins_epoch_interp_ar.set...
Not setting metadata
304 matching events found
No baseline correction applied
0 projection items activated
Ready.
    Rejecting  epoch based on EEG : ['P7']
    Rejecting  epoch based on EEG : ['Oz']
    Rejecting  epoch based on EEG : ['Fz']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['Oz']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['Oz', 'O2']
    Rejecting  epoch based on EEG : ['Oz']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['Oz']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['PO8']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['Oz']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['Oz']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
    Rejecting  epoch based on EEG : ['O2']
39 bad epochs dropped
Extracting parameters from e:\论文写作\论文2数据分析\N170\N170_Data\9_N170_shifted_ds_reref_ucbip_hpfilt_ica_corr_cbip_elist_bins_epoch_interp_ar.set...

C:\Users\Administrator\AppData\Local\Temp\ipykernel_6512\2407259580.py:12: RuntimeWarning: At least one epoch has multiple events. Only the latency of the first event will be retained.
  epo = mne.io.read_epochs_eeglab(file_name);
C:\Users\Administrator\AppData\Local\Temp\ipykernel_6512\2407259580.py:12: RuntimeWarning: At least one epoch has multiple events. Only the latency of the first event will be retained.
  epo = mne.io.read_epochs_eeglab(file_name);

erp_data_mean = np.mean(erp_data, axis=0) #[2, 28, 256]

erp_data_norm = erp_data_mean * 1e6

sub_num = erp_data.shape[0]
type_num = erp_data_mean.shape[0]
ch_num = erp_data_mean.shape[1]
time_num = erp_data_mean.shape[2]

info_tmp = mne.create_info(ch_names=epo.ch_names, sfreq=256, ch_types='eeg')

erp1 = mne.EvokedArray(erp_data_mean[0], info_tmp, tmin=-0.2, nave=None)
erp1.set_montage(epo.get_montage());

erp2 = mne.EvokedArray(erp_data_mean[1], info_tmp, tmin=-0.2, nave=None)
erp2.set_montage(epo.get_montage());

erp_diff = mne.EvokedArray(erp_data_mean[0]-erp_data_mean[1], info_tmp, tmin=-0.2, nave=None)
erp_diff.set_montage(epo.get_montage());

fig = erp1.plot(gfp=True, ylim = dict(eeg=[-12, 10]));

fig = erp2.plot(gfp=True, ylim = dict(eeg=[-12, 10]));

fig = erp_diff.plot(gfp=True, ylim = dict(eeg=[-8, 5]));

tp_args = { "vlim":(-3, 3), "time_format":'%3.2f', "contours":10, "cmap":"jet" }
erp_diff.plot_joint(title='Faces minus Cars', times=[0.13, 0.18, 0.25, 0.35, 0.55], topomap_args=tp_args);

No projector specified for this dataset. Please consider the method self.add_proj.

erp_diff.plot_topomap(cmap="jet", vlim=[-3, 3], time_format='%3.2f', 
                      times=[0.13, 0.17, 0.2, 0.25, 0.35, 0.4, 0.45, 0.55, 0.6, 0.65], nrows=1 );

ch_index = epo.ch_names.index('PO8')

erp_data_1 = erp_data_mean[0][ch_index] * 1e6
erp_data_2 = erp_data_mean[1][ch_index] * 1e6

n_sub = erp_data.shape[0] # [40, 2, 28, 256] 
erp_data_diff_sem = np.std((erp_data[:,0,ch_index]-erp_data[:,1,ch_index]) * 1e6, axis=0, ddof=0)/np.sqrt(n_sub)

colors = sns.color_palette('Set2')

plt.figure(figsize=(3.5, 2))

ax = plt.gca()
# ax.axvspan(0, 100, alpha=0.1, color='grey')
plt.grid(color='gray', linewidth=0.5, alpha=0.5, linestyle='-')
plt.axhline(0.0, color='k', linewidth=1.0, linestyle=':', alpha=0.5)
plt.axvline(51.2, color='k', linewidth=1.0, linestyle=':', alpha=0.5)

# filter
mean_line1 = savgol_filter(erp_data_1, 4, 2) # win_size: 4, order: 3
mean_line2 = savgol_filter(erp_data_2, 4, 2) # win_size: 4, order: 3

diff_line = mean_line1 - mean_line2
sem_line1 = diff_line - erp_data_diff_sem
sem_line2 = diff_line + erp_data_diff_sem

plt.plot(mean_line1, label='Faces', color=colors[0])    
plt.plot(mean_line2, label='Cars', color=colors[1])
plt.plot(diff_line, label='Faces minus Cars', linewidth=1.0, color=colors[2])

plt.fill_between(range(256), sem_line1, sem_line2, alpha=0.5, label='SEM', color=colors[2] )    

ax.xaxis.set_minor_locator(MultipleLocator(12.8))
plt.xlim([0,256])
plt.ylim([-8, 10])
    
plt.legend(prop={'family':'Times New Roman', 'size':9}, ncol = 1, bbox_to_anchor=(1.0, 1.0))

font = {'family' : 'Times New Roman', # 'Microsoft YaHei' 'SimHei' 'serif' 
        'color'  : 'k',
        'weight' : 'normal',
        'size'   : 10,
        }

plt.xticks(np.linspace(0, 256, 11, endpoint=True), ['-0.2', '',  '0.0', '', '0.2', '', '0.4', '', '0.6', '', '0.8'], fontdict=font);
# ['-0.2', '-0.1',  '0.0', '0.1', '0.2', '0.3', '0.4', '0.5', '0.6', '0.7', '0.8']
plt.xlabel("Time (s)", fontdict=font)
plt.yticks(np.linspace(-8, 10, 4, endpoint=True), np.linspace(-8, 10, 4, endpoint=True), fontdict=font);
plt.ylabel("PO8 (uV)", fontdict=font);

# time [-0.2, 0.8] 256Hz 
# epo.time_as_index(0.0)  51
# epo.time_as_index(0.7)  231
# slide_window 0.1s [-12, 12]

half_win = 12

start_t = 51
end_t = 231
len_t = 180

cov_mat = 0
cov_diag = 0
cov_data = 0
crop_erp = 0

flag = 0
for tp in range(type_num):

    data = erp_data_norm[tp]

    cov_mat_epoch = np.empty((len_t, ch_num, ch_num))
    cov_data_epoch = np.empty(( len_t, int(ch_num*((ch_num+1)/2)) ))
    cov_diag_epoch = np.empty(( len_t, ch_num ))

    for ind, t in enumerate(range(start_t, end_t)):
        # calculate covariance matrix
        cov = np.cov(data[:, t-half_win:t+half_win])
        # get the triangle elements of the matrix
        cov_data_epoch[ind] = cov[np.triu_indices(cov.shape[0], k=0)]
        cov_diag_epoch[ind] = np.diagonal(cov)
        # shrunk
        cov = shrunk_covariance(cov, shrinkage=0.01)
        cov_mat_epoch[ind] = cov
                
    if flag == 0:
        flag = 1
        cov_mat = cov_mat_epoch
        cov_diag = cov_diag_epoch
        cov_data = cov_data_epoch
        crop_erp = erp_data_mean[tp, :, start_t:end_t].T
    else:
        cov_data = np.vstack((cov_data, cov_data_epoch))
        cov_diag = np.vstack((cov_diag, cov_diag_epoch))
        cov_mat = np.vstack((cov_mat, cov_mat_epoch))
        crop_erp = np.vstack((crop_erp, erp_data_mean[tp, :, start_t:end_t].T))

print( crop_erp.shape ) # [times, chs]
print( cov_mat.shape )  # [times, chs, chs]
print( cov_diag.shape ) # [times, chs]
print( cov_data.shape ) # [times, diag] # 14 * 29
print( type_num*len_t, int(ch_num*((ch_num+1)/2)) ) # 360 = 2 * 180

(360, 28)
(360, 28, 28)
(360, 28)
(360, 406)
360 406

# with open('./tmp_data/raw_eeg_data.pkl', 'wb') as f:
#     dill.dump([erp_data, erp_data_mean, cov_mat, cov_data, cov_diag, crop_erp], f)

with open('./tmp_data/raw_eeg_data.pkl', 'rb') as f:
    [erp_data, erp_data_mean, cov_mat, cov_data, cov_diag, crop_erp] = dill.load(f)

def draw_cov_mat(ind):
    fig, ax = plt.subplots(figsize=(1.5, 1.5))
    ax0 = ax.matshow(cov_mat[ind], interpolation='none', vmin=-2, vmax=2.0, cmap='jet');# cmap='turbo', 
    clb = fig.colorbar(ax0, fraction=0.045);
    ax.xaxis.set_ticks_position("bottom")
    plt.grid(color='gray', linestyle=':', linewidth=0.5);
    clb.set_ticks(ticks=[-2, 0, 2])
    cbar_label = clb.ax.get_xticklabels() + clb.ax.get_yticklabels()
    [lab.set_font('Times New Roman') for lab in cbar_label]  #Times New Roman Arial
    clb.ax.tick_params(labelsize=10)
    ax.set_xticks(np.arange(0,30,10), np.arange(0,30,10), fontdict=font);
    ax.set_yticks(np.arange(0,30,10), np.arange(0,30,10), fontdict=font);
    plt.show();

tps = [20, 50, 80]
for tp in tps:
    draw_cov_mat(tp)

%%writefile calc_dist_o_fun.py

import scipy
import numpy as np

def calc_dist_o(cov1, cov2):
    evals, _ = scipy.linalg.eigh(cov1,cov2)
    res = evals[-1] #np.max(evals) 
    
    return res

Overwriting calc_dist_o_fun.py

import calc_dist_o_fun
import multiprocessing

num_cores = int(multiprocessing.cpu_count())

print("CPU cores: ", num_cores)

CPU cores:  32

tp = cov_mat.shape[0]

cov_dist_o = np.full((tp, tp), np.nan)

for i in range(tp):
    if i % 200 == 0: # ~3min
        print(i)
 
    pool = multiprocessing.Pool(processes = num_cores)
    res = []
    for j in range(i+1, tp):        
        r = pool.apply_async(calc_dist_o_fun.calc_dist_o, args=( cov_mat[i], cov_mat[j] )) 
        res.append(r)

    pool.close()

    evals_i = np.squeeze( [p.get() for p in res] )
    cov_dist_o[i, i+1:] = evals_i

0
200

# with open('./tmp_data/cov_dist_o.pkl', 'wb') as f:
#     dill.dump(cov_dist_o, f)

with open('./tmp_data/cov_dist_o.pkl', 'rb') as f:
    cov_dist_o = dill.load(f)

fig, ax = plt.subplots(figsize=(1.7, 1.7))
ax0 = ax.matshow(np.log(cov_dist_o), interpolation='none', vmin=1.0, vmax=11.0, cmap='jet');
clb = fig.colorbar(ax0, fraction=0.045);
ax.xaxis.set_ticks_position("bottom")
plt.grid(color='gray', linestyle=':', linewidth=0.5);
clb.set_ticks(ticks=[1, 6, 11])
cbar_label = clb.ax.get_xticklabels() + clb.ax.get_yticklabels()
[lab.set_font('Arial') for lab in cbar_label]  #Times New Roman  #set_fontstyle
clb.ax.tick_params(labelsize=10)
ax.set_xticks(np.arange(0,401,100), np.arange(0,401,100), fontdict=font);
ax.set_yticks(np.arange(0,401,100), np.arange(0,401,100), fontdict=font);
plt.show();

norm_cov_dist_o = np.log(cov_dist_o)
norm_cov_dist_o /= (np.nanmax(norm_cov_dist_o))

fig, ax = plt.subplots(figsize=(1.7, 1.7))
ax0 = ax.matshow(norm_cov_dist_o, interpolation='none', vmin=0.0, vmax=1.0, cmap='jet', );
clb = fig.colorbar(ax0, fraction=0.045);
ax.xaxis.set_ticks_position("bottom")
plt.grid(color='gray', linestyle=':', linewidth=0.5);
clb.set_ticks(ticks=[0, 0.5, 1])
cbar_label = clb.ax.get_xticklabels() + clb.ax.get_yticklabels()
[lab.set_font('Arial') for lab in cbar_label] 
clb.ax.tick_params(labelsize=10)
ax.set_xticks(np.arange(0,401,100), np.arange(0,401,100), fontdict=font);
ax.set_yticks(np.arange(0,401,100), np.arange(0,401,100), fontdict=font);
plt.show();

%%writefile calc_dist_s_fun.py

import scipy
import numpy as np

def calc_dist_s(cov1, cov2):

    d2 = (np.log(scipy.linalg.eigvalsh(cov1,cov2))**2).sum(axis=-1)
    riemann_dist = np.sqrt(d2) 
    
    return riemann_dist

Overwriting calc_dist_s_fun.py

import calc_dist_s_fun
import multiprocessing

num_cores = int(multiprocessing.cpu_count())

print("CPU cores: ", num_cores)

CPU cores:  32

tp = cov_mat.shape[0]

cov_dist_s = np.full((tp, tp), np.nan)

for i in range(tp):
    if i % 200 == 0: # ~3min
        print(i)

    pool = multiprocessing.Pool(processes = num_cores)
    res = []
    for j in range(i+1, tp):        
        r = pool.apply_async(calc_dist_s_fun.calc_dist_s, args=( cov_mat[i], cov_mat[j] ))
        res.append(r)

    pool.close()

    riemann_dist_i = np.squeeze( [p.get() for p in res] )
    cov_dist_s[i, i+1:] = riemann_dist_i

0
200

# with open('./tmp_data/cov_dist_s.pkl', 'wb') as f:
#     dill.dump(cov_dist_s, f)

with open('./tmp_data/cov_dist_s.pkl', 'rb') as f:
    cov_dist_s = dill.load(f)

fig, ax = plt.subplots(figsize=(1.7, 1.7))
ax0 = ax.matshow(cov_dist_s, interpolation='none', vmin=0.0, vmax=20.0, cmap='jet', );# 
clb = fig.colorbar(ax0, fraction=0.045);
ax.xaxis.set_ticks_position("bottom")
plt.grid(color='gray', linestyle=':', linewidth=0.5);
clb.set_ticks(ticks=[0, 10, 20])
cbar_label = clb.ax.get_xticklabels() + clb.ax.get_yticklabels()
[lab.set_font('Arial') for lab in cbar_label]  #Times New Roman  #set_fontstyle
clb.ax.tick_params(labelsize=10)

ax.set_xticks(np.arange(0,401,100), np.arange(0,401,100), fontdict=font);
ax.set_yticks(np.arange(0,401,100), np.arange(0,401,100), fontdict=font);
plt.show();

norm_cov_dist_s = copy.deepcopy(cov_dist_s)
norm_cov_dist_s /= (np.nanmax(norm_cov_dist_s))

fig, ax = plt.subplots(figsize=(1.7, 1.7))
ax0 = ax.matshow(norm_cov_dist_s, interpolation='none', vmin=0.0, vmax=1.0, cmap='jet', );
clb = fig.colorbar(ax0, fraction=0.045);
ax.xaxis.set_ticks_position("bottom")
plt.grid(color='gray', linestyle=':', linewidth=0.5);
clb.set_ticks(ticks=[0, 0.5, 1])
cbar_label = clb.ax.get_xticklabels() + clb.ax.get_yticklabels()
[lab.set_font('Arial') for lab in cbar_label]
clb.ax.tick_params(labelsize=10)

ax.set_xticks(np.arange(0,401,100), np.arange(0,401,100), fontdict=font);
ax.set_yticks(np.arange(0,401,100), np.arange(0,401,100), fontdict=font);
plt.show();

norm_dist_o_symm = np.ones_like(norm_cov_dist_o)
for i in range(norm_cov_dist_o.shape[0]):
    for j in range(i+1, norm_cov_dist_o.shape[0]):
        norm_dist_o_symm[i,j] = norm_cov_dist_o[i,j]
        norm_dist_o_symm[j,i] = norm_cov_dist_o[i,j]

mds = MDS(n_components=28, dissimilarity='precomputed', metric=True, 
          n_jobs=32, random_state=3, normalized_stress='auto') 
features_dist_o = mds.fit_transform(norm_dist_o_symm)

features_dist_o.shape

(360, 28)

norm_dist_s_symm = np.ones_like(norm_cov_dist_s)
for i in range(norm_cov_dist_s.shape[0]):
    for j in range(i+1, norm_cov_dist_s.shape[0]):
        norm_dist_s_symm[i,j] = norm_cov_dist_s[i,j]
        norm_dist_s_symm[j,i] = norm_cov_dist_s[i,j]

mds = MDS(n_components=28, dissimilarity='precomputed', metric=True, 
          n_jobs=32, random_state=3, normalized_stress='auto')
features_dist_s = mds.fit_transform(norm_dist_s_symm)

features_dist_s.shape

(360, 28)

# with open('./tmp_data/distance_mds_data.pkl', 'wb') as f:
#     dill.dump([features_dist_o, features_dist_s], f)

with open('./tmp_data/distance_mds_data.pkl', 'rb') as f:
    [features_dist_o, features_dist_s] = dill.load(f)

norm_cov_diag = np.log(10*cov_diag)

norm_dist_o = 20*features_dist_o

norm_dist_s = 20*features_dist_s

import warnings
warnings.filterwarnings('ignore')

font = {'family':['Times New Roman', 'Arial', ], 'weight':'normal', 'size':10 }
colors = sns.color_palette('Set2')

plt.figure(figsize=(2.5, 1.5))

sns.histplot(norm_cov_diag.flatten()-0.4, bins=80, stat='density', legend=False, color=colors[0], alpha=0.8, )
sns.histplot(norm_dist_o.flatten()+0.2, bins=80, stat='density', legend=False, color=colors[1], alpha=0.8, )
sns.histplot(norm_dist_s.flatten()-0.2, bins=80, stat='density', legend=False, color=colors[2], alpha=0.8, )

plt.xlim([-5, 5])
plt.ylim([0, 0.4])

plt.legend(labels=['Diagonal elements', 'Distance o', 'Distance s'], prop=font, bbox_to_anchor=(1.0, 1.0));

input_data_raw = np.hstack((norm_cov_diag, norm_dist_o, norm_dist_s))
print(input_data_raw.shape) #[360, 84]

input_data = torch.from_numpy(input_data_raw).type(torch.FloatTensor) #[samples, features]

device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
print(device)

(360, 84)
cuda:0

tsne = TSNE(n_components=2, init='pca', random_state=0, n_jobs=-1, perplexity=30)

for data in [norm_cov_diag, norm_dist_o, norm_dist_s, input_data_raw]:
    tsne_2d = tsne.fit_transform(data)

    fig, axi1=plt.subplots(1, figsize=(2, 1.5))    
    axi1.scatter(tsne_2d[:, 0], tsne_2d[:, 1],
                marker='*', s=10, color=sns.color_palette('Paired')[1],
                )

    ax = plt.gca()
    plt.grid(True, linewidth=0.5, color='gray', linestyle=':')
    plt.xlim([-40, 40])
    plt.ylim([-40, 40])
    # plt.yticks([-100,-50,0,50,100],[-100,-50,0,50,100])
    # plt.xticks([-100,-50,0,50,100],[-100,-50,0,50,100])

    ax.tick_params(which='both', bottom=True, top=False, left=True, right=False,
                labelbottom=True, labelleft=True, direction='out',width=1)
    plt.show()

# with open('./tmp_data/network_input_data.pkl', 'wb') as f:
#     dill.dump([norm_cov_diag, norm_dist_o, norm_dist_s, input_data_raw], f)

with open('./tmp_data/network_input_data.pkl', 'rb') as f:
    [norm_cov_diag, norm_dist_o, norm_dist_s, input_data_raw] = dill.load(f)

import importlib

importlib.reload(UDEC_Network)

<module 'utils.UDEC_Network' from 'e:\\论文写作\\论文2\\N170\\utils\\UDEC_Network.py'>

EPOCHS_PRE = 1001
LR_PRE = 1e-3 # dynamic adjust learning rate
BATCH_SIZE = 32

autoencoder = UDEC_Network.AutoEncoder().to(device)
checkpoint = { "epoch": 0, "best": float("inf") }
file_path_prefix = './network_data/'
ae_save_path = file_path_prefix + 'autoencoder.pth'

UDEC_Network.pretrain(data=input_data, model=autoencoder, savepath=ae_save_path, 
                      checkpoint=checkpoint, file_path_prefix=file_path_prefix, 
                      num_epochs=EPOCHS_PRE, batch_size=BATCH_SIZE, lr=LR_PRE)

epoch [1/1001], MSE_loss:2.20673
epoch [2/1001], MSE_loss:1.69884
epoch [3/1001], MSE_loss:1.60556
epoch [4/1001], MSE_loss:1.15251
epoch [5/1001], MSE_loss:1.40224
epoch [6/1001], MSE_loss:1.32023
epoch [7/1001], MSE_loss:1.00663
epoch [8/1001], MSE_loss:1.12145
epoch [9/1001], MSE_loss:1.13765
epoch [10/1001], MSE_loss:0.95416
epoch [11/1001], MSE_loss:0.88185
epoch [12/1001], MSE_loss:0.85678
epoch [13/1001], MSE_loss:0.91871
epoch [14/1001], MSE_loss:1.07839
epoch [15/1001], MSE_loss:0.93291
epoch [16/1001], MSE_loss:0.60339
epoch [17/1001], MSE_loss:0.71961
epoch [18/1001], MSE_loss:0.77097
epoch [19/1001], MSE_loss:0.76433
epoch [20/1001], MSE_loss:0.57989
epoch [21/1001], MSE_loss:0.57952
epoch [22/1001], MSE_loss:0.60240
epoch [23/1001], MSE_loss:0.48501
epoch [24/1001], MSE_loss:0.57349
epoch [25/1001], MSE_loss:0.58310
epoch [26/1001], MSE_loss:0.56255
epoch [27/1001], MSE_loss:0.33552
epoch [28/1001], MSE_loss:0.35851
epoch [29/1001], MSE_loss:0.61156
epoch [30/1001], MSE_loss:0.39084
epoch [31/1001], MSE_loss:0.37091
epoch [32/1001], MSE_loss:0.35287
epoch [33/1001], MSE_loss:0.43826
epoch [34/1001], MSE_loss:0.35670
epoch [35/1001], MSE_loss:0.29774
epoch [36/1001], MSE_loss:0.34316
epoch [37/1001], MSE_loss:0.35239
epoch [38/1001], MSE_loss:0.22703
epoch [39/1001], MSE_loss:0.32963
epoch [40/1001], MSE_loss:0.20045
epoch [41/1001], MSE_loss:0.27567
epoch [42/1001], MSE_loss:0.29175
epoch [43/1001], MSE_loss:0.24494
epoch [44/1001], MSE_loss:0.41978
epoch [45/1001], MSE_loss:0.19462
epoch [46/1001], MSE_loss:0.40880
epoch [47/1001], MSE_loss:0.22659
epoch [48/1001], MSE_loss:0.30915
epoch [49/1001], MSE_loss:0.19052
epoch [50/1001], MSE_loss:0.30192
epoch [51/1001], MSE_loss:0.20930
epoch [52/1001], MSE_loss:0.27116
epoch [53/1001], MSE_loss:0.16056
epoch [54/1001], MSE_loss:0.22014
epoch [55/1001], MSE_loss:0.14707
epoch [56/1001], MSE_loss:0.21644
epoch [57/1001], MSE_loss:0.16952
epoch [58/1001], MSE_loss:0.15855
epoch [59/1001], MSE_loss:0.24304
epoch [60/1001], MSE_loss:0.17185
epoch [61/1001], MSE_loss:0.22718
epoch [62/1001], MSE_loss:0.25111
epoch [63/1001], MSE_loss:0.12722
epoch [64/1001], MSE_loss:0.19231
epoch [65/1001], MSE_loss:0.12721
epoch [66/1001], MSE_loss:0.18179
epoch [67/1001], MSE_loss:0.25557
epoch [68/1001], MSE_loss:0.17803
epoch [69/1001], MSE_loss:0.14923
epoch [70/1001], MSE_loss:0.15304
epoch [71/1001], MSE_loss:0.15182
epoch [72/1001], MSE_loss:0.24789
epoch [73/1001], MSE_loss:0.16949
epoch [74/1001], MSE_loss:0.12914
epoch [75/1001], MSE_loss:0.19416
epoch [76/1001], MSE_loss:0.17848
epoch [77/1001], MSE_loss:0.11434
epoch [78/1001], MSE_loss:0.13698
epoch [79/1001], MSE_loss:0.15275
epoch [80/1001], MSE_loss:0.19928
epoch [81/1001], MSE_loss:0.09819
epoch [82/1001], MSE_loss:0.18294
epoch [83/1001], MSE_loss:0.12370
epoch [84/1001], MSE_loss:0.17777
epoch [85/1001], MSE_loss:0.12016
epoch [86/1001], MSE_loss:0.19530
epoch [87/1001], MSE_loss:0.12373
epoch [88/1001], MSE_loss:0.11769
epoch [89/1001], MSE_loss:0.12227
epoch [90/1001], MSE_loss:0.13812
epoch [91/1001], MSE_loss:0.09486
epoch [92/1001], MSE_loss:0.15045
epoch [93/1001], MSE_loss:0.13865
epoch [94/1001], MSE_loss:0.14318
epoch [95/1001], MSE_loss:0.10496
epoch [96/1001], MSE_loss:0.14417
epoch [97/1001], MSE_loss:0.15552
epoch [98/1001], MSE_loss:0.11921
epoch [99/1001], MSE_loss:0.08620
epoch [100/1001], MSE_loss:0.13877
epoch [101/1001], MSE_loss:0.13510
epoch [102/1001], MSE_loss:0.14900
epoch [103/1001], MSE_loss:0.14954
epoch [104/1001], MSE_loss:0.14553
epoch [105/1001], MSE_loss:0.15056
epoch [106/1001], MSE_loss:0.13442
epoch [107/1001], MSE_loss:0.14164
epoch [108/1001], MSE_loss:0.07257
epoch [109/1001], MSE_loss:0.12979
epoch [110/1001], MSE_loss:0.12023
epoch [111/1001], MSE_loss:0.18953
epoch [112/1001], MSE_loss:0.11345
epoch [113/1001], MSE_loss:0.12136
epoch [114/1001], MSE_loss:0.10853
epoch [115/1001], MSE_loss:0.12759
epoch [116/1001], MSE_loss:0.14842
epoch [117/1001], MSE_loss:0.13462
epoch [118/1001], MSE_loss:0.13044
epoch [119/1001], MSE_loss:0.08280
epoch [120/1001], MSE_loss:0.11419
epoch [121/1001], MSE_loss:0.09377
epoch [122/1001], MSE_loss:0.13811
epoch [123/1001], MSE_loss:0.16838
epoch [124/1001], MSE_loss:0.13371
epoch [125/1001], MSE_loss:0.13370
epoch [126/1001], MSE_loss:0.09641
epoch [127/1001], MSE_loss:0.16017
epoch [128/1001], MSE_loss:0.14553
epoch [129/1001], MSE_loss:0.09075
epoch [130/1001], MSE_loss:0.07740
epoch [131/1001], MSE_loss:0.11045
epoch [132/1001], MSE_loss:0.10269
epoch [133/1001], MSE_loss:0.10673
epoch [134/1001], MSE_loss:0.13350
epoch [135/1001], MSE_loss:0.13600
epoch [136/1001], MSE_loss:0.14457
epoch [137/1001], MSE_loss:0.09054
epoch [138/1001], MSE_loss:0.14899
epoch [139/1001], MSE_loss:0.12148
epoch [140/1001], MSE_loss:0.13164
epoch [141/1001], MSE_loss:0.11163
epoch [142/1001], MSE_loss:0.09541
epoch [143/1001], MSE_loss:0.08839
epoch [144/1001], MSE_loss:0.10428
epoch [145/1001], MSE_loss:0.12167
epoch [146/1001], MSE_loss:0.10570
epoch [147/1001], MSE_loss:0.12564
epoch [148/1001], MSE_loss:0.10296
epoch [149/1001], MSE_loss:0.11086
epoch [150/1001], MSE_loss:0.13406
epoch [151/1001], MSE_loss:0.09981
epoch [152/1001], MSE_loss:0.08836
epoch [153/1001], MSE_loss:0.11253
epoch [154/1001], MSE_loss:0.13942
epoch [155/1001], MSE_loss:0.13966
epoch [156/1001], MSE_loss:0.14046
epoch [157/1001], MSE_loss:0.12902
epoch [158/1001], MSE_loss:0.15664
epoch [159/1001], MSE_loss:0.11810
epoch [160/1001], MSE_loss:0.12561
epoch [161/1001], MSE_loss:0.11242
epoch [162/1001], MSE_loss:0.10697
epoch [163/1001], MSE_loss:0.10908
epoch [164/1001], MSE_loss:0.14509
epoch [165/1001], MSE_loss:0.09596
epoch [166/1001], MSE_loss:0.12093
epoch [167/1001], MSE_loss:0.11627
epoch [168/1001], MSE_loss:0.12473
epoch [169/1001], MSE_loss:0.12562
epoch [170/1001], MSE_loss:0.10943
epoch [171/1001], MSE_loss:0.12478
epoch [172/1001], MSE_loss:0.13384
epoch [173/1001], MSE_loss:0.10338
epoch [174/1001], MSE_loss:0.12036
epoch [175/1001], MSE_loss:0.11596
epoch [176/1001], MSE_loss:0.08952
epoch [177/1001], MSE_loss:0.13004
epoch [178/1001], MSE_loss:0.11588
epoch [179/1001], MSE_loss:0.12029
epoch [180/1001], MSE_loss:0.10331
epoch [181/1001], MSE_loss:0.14649
epoch [182/1001], MSE_loss:0.09187
epoch [183/1001], MSE_loss:0.13910
epoch [184/1001], MSE_loss:0.15530
epoch [185/1001], MSE_loss:0.08762
epoch [186/1001], MSE_loss:0.09107
epoch [187/1001], MSE_loss:0.11364
epoch [188/1001], MSE_loss:0.11179
epoch [189/1001], MSE_loss:0.18457
epoch [190/1001], MSE_loss:0.15415
epoch [191/1001], MSE_loss:0.13805
epoch [192/1001], MSE_loss:0.12605
epoch [193/1001], MSE_loss:0.10304
epoch [194/1001], MSE_loss:0.14352
epoch [195/1001], MSE_loss:0.11438
epoch [196/1001], MSE_loss:0.11290
epoch [197/1001], MSE_loss:0.10447
epoch [198/1001], MSE_loss:0.09320
epoch [199/1001], MSE_loss:0.07913
epoch [200/1001], MSE_loss:0.12487
epoch [201/1001], MSE_loss:0.11366
epoch [202/1001], MSE_loss:0.09969
epoch [203/1001], MSE_loss:0.19552
epoch [204/1001], MSE_loss:0.14293
epoch [205/1001], MSE_loss:0.11861
epoch [206/1001], MSE_loss:0.13058
epoch [207/1001], MSE_loss:0.14337
epoch [208/1001], MSE_loss:0.14676
epoch [209/1001], MSE_loss:0.12713
epoch [210/1001], MSE_loss:0.09847
epoch [211/1001], MSE_loss:0.14421
epoch [212/1001], MSE_loss:0.14396
epoch [213/1001], MSE_loss:0.09850
epoch [214/1001], MSE_loss:0.10587
epoch [215/1001], MSE_loss:0.16295
epoch [216/1001], MSE_loss:0.13042
epoch [217/1001], MSE_loss:0.13344
epoch [218/1001], MSE_loss:0.13570
epoch [219/1001], MSE_loss:0.13232
epoch [220/1001], MSE_loss:0.11656
epoch [221/1001], MSE_loss:0.11702
epoch [222/1001], MSE_loss:0.17779
epoch [223/1001], MSE_loss:0.15732
epoch [224/1001], MSE_loss:0.08197
epoch [225/1001], MSE_loss:0.09219
epoch [226/1001], MSE_loss:0.14909
epoch [227/1001], MSE_loss:0.15757
epoch [228/1001], MSE_loss:0.12113
epoch [229/1001], MSE_loss:0.13810
epoch [230/1001], MSE_loss:0.11304
epoch [231/1001], MSE_loss:0.13489
epoch [232/1001], MSE_loss:0.09452
epoch [233/1001], MSE_loss:0.15090
epoch [234/1001], MSE_loss:0.13620
epoch [235/1001], MSE_loss:0.12744
epoch [236/1001], MSE_loss:0.11064
epoch [237/1001], MSE_loss:0.08609
epoch [238/1001], MSE_loss:0.11829
epoch [239/1001], MSE_loss:0.15263
epoch [240/1001], MSE_loss:0.13834
epoch [241/1001], MSE_loss:0.13530
epoch [242/1001], MSE_loss:0.14441
epoch [243/1001], MSE_loss:0.11443
epoch [244/1001], MSE_loss:0.08736
epoch [245/1001], MSE_loss:0.13784
epoch [246/1001], MSE_loss:0.10011
epoch [247/1001], MSE_loss:0.11628
epoch [248/1001], MSE_loss:0.11119
epoch [249/1001], MSE_loss:0.12027
epoch [250/1001], MSE_loss:0.09651
epoch [251/1001], MSE_loss:0.11381
epoch [252/1001], MSE_loss:0.10222
epoch [253/1001], MSE_loss:0.11193
epoch [254/1001], MSE_loss:0.15913
epoch [255/1001], MSE_loss:0.14841
epoch [256/1001], MSE_loss:0.10883
epoch [257/1001], MSE_loss:0.11473
epoch [258/1001], MSE_loss:0.15752
epoch [259/1001], MSE_loss:0.15380
epoch [260/1001], MSE_loss:0.09266
epoch [261/1001], MSE_loss:0.11785
epoch [262/1001], MSE_loss:0.14944
epoch [263/1001], MSE_loss:0.14936
epoch [264/1001], MSE_loss:0.12503
epoch [265/1001], MSE_loss:0.14587
epoch [266/1001], MSE_loss:0.12915
epoch [267/1001], MSE_loss:0.14154
epoch [268/1001], MSE_loss:0.13551
epoch [269/1001], MSE_loss:0.16426
epoch [270/1001], MSE_loss:0.09834
epoch [271/1001], MSE_loss:0.12038
epoch [272/1001], MSE_loss:0.09750
epoch [273/1001], MSE_loss:0.11577
epoch [274/1001], MSE_loss:0.12231
epoch [275/1001], MSE_loss:0.14480
epoch [276/1001], MSE_loss:0.10046
epoch [277/1001], MSE_loss:0.09848
epoch [278/1001], MSE_loss:0.11306
epoch [279/1001], MSE_loss:0.09945
epoch [280/1001], MSE_loss:0.14194
epoch [281/1001], MSE_loss:0.09261
epoch [282/1001], MSE_loss:0.12079
epoch [283/1001], MSE_loss:0.08891
epoch [284/1001], MSE_loss:0.12582
epoch [285/1001], MSE_loss:0.12513
epoch [286/1001], MSE_loss:0.16916
epoch [287/1001], MSE_loss:0.12004
epoch [288/1001], MSE_loss:0.14086
epoch [289/1001], MSE_loss:0.10150
epoch [290/1001], MSE_loss:0.12403
epoch [291/1001], MSE_loss:0.12192
epoch [292/1001], MSE_loss:0.06397
epoch [293/1001], MSE_loss:0.10255
epoch [294/1001], MSE_loss:0.10918
epoch [295/1001], MSE_loss:0.10749
epoch [296/1001], MSE_loss:0.09151
epoch [297/1001], MSE_loss:0.14164
epoch [298/1001], MSE_loss:0.10808
epoch [299/1001], MSE_loss:0.12964
epoch [300/1001], MSE_loss:0.09754
epoch [301/1001], MSE_loss:0.10554
epoch [302/1001], MSE_loss:0.12259
epoch [303/1001], MSE_loss:0.07521
epoch [304/1001], MSE_loss:0.13341
epoch [305/1001], MSE_loss:0.10748
epoch [306/1001], MSE_loss:0.13401
epoch [307/1001], MSE_loss:0.13462
epoch [308/1001], MSE_loss:0.09277
epoch [309/1001], MSE_loss:0.13084
epoch [310/1001], MSE_loss:0.15306
epoch [311/1001], MSE_loss:0.12298
epoch [312/1001], MSE_loss:0.11568
epoch [313/1001], MSE_loss:0.16917
epoch [314/1001], MSE_loss:0.11130
epoch [315/1001], MSE_loss:0.09718
epoch [316/1001], MSE_loss:0.07102
epoch [317/1001], MSE_loss:0.08788
epoch [318/1001], MSE_loss:0.09731
epoch [319/1001], MSE_loss:0.13727
epoch [320/1001], MSE_loss:0.13181
epoch [321/1001], MSE_loss:0.14220
epoch [322/1001], MSE_loss:0.11772
epoch [323/1001], MSE_loss:0.09391
epoch [324/1001], MSE_loss:0.09930
epoch [325/1001], MSE_loss:0.09014
epoch [326/1001], MSE_loss:0.14990
epoch [327/1001], MSE_loss:0.09148
epoch [328/1001], MSE_loss:0.13349
epoch [329/1001], MSE_loss:0.13258
epoch [330/1001], MSE_loss:0.08945
epoch [331/1001], MSE_loss:0.09507
epoch [332/1001], MSE_loss:0.09502
epoch [333/1001], MSE_loss:0.16130
epoch [334/1001], MSE_loss:0.12025
epoch [335/1001], MSE_loss:0.11965
epoch [336/1001], MSE_loss:0.09494
epoch [337/1001], MSE_loss:0.12115
epoch [338/1001], MSE_loss:0.09983
epoch [339/1001], MSE_loss:0.13291
epoch [340/1001], MSE_loss:0.11476
epoch [341/1001], MSE_loss:0.16675
epoch [342/1001], MSE_loss:0.11194
epoch [343/1001], MSE_loss:0.11105
epoch [344/1001], MSE_loss:0.10620
epoch [345/1001], MSE_loss:0.12150
epoch [346/1001], MSE_loss:0.10749
epoch [347/1001], MSE_loss:0.13071
epoch [348/1001], MSE_loss:0.09939
epoch [349/1001], MSE_loss:0.08899
epoch [350/1001], MSE_loss:0.09642
epoch [351/1001], MSE_loss:0.12097
epoch [352/1001], MSE_loss:0.09684
epoch [353/1001], MSE_loss:0.14472
epoch [354/1001], MSE_loss:0.11700
epoch [355/1001], MSE_loss:0.12878
epoch [356/1001], MSE_loss:0.11697
epoch [357/1001], MSE_loss:0.12495
epoch [358/1001], MSE_loss:0.10586
epoch [359/1001], MSE_loss:0.08542
epoch [360/1001], MSE_loss:0.09859
epoch [361/1001], MSE_loss:0.14643
epoch [362/1001], MSE_loss:0.14387
epoch [363/1001], MSE_loss:0.14188
epoch [364/1001], MSE_loss:0.13689
epoch [365/1001], MSE_loss:0.12904
epoch [366/1001], MSE_loss:0.14607
epoch [367/1001], MSE_loss:0.12627
epoch [368/1001], MSE_loss:0.14027
epoch [369/1001], MSE_loss:0.14689
epoch [370/1001], MSE_loss:0.09985
epoch [371/1001], MSE_loss:0.11650
epoch [372/1001], MSE_loss:0.14520
epoch [373/1001], MSE_loss:0.11534
epoch [374/1001], MSE_loss:0.09816
epoch [375/1001], MSE_loss:0.11294
epoch [376/1001], MSE_loss:0.09649
epoch [377/1001], MSE_loss:0.14971
epoch [378/1001], MSE_loss:0.09409
epoch [379/1001], MSE_loss:0.07680
epoch [380/1001], MSE_loss:0.11752
epoch [381/1001], MSE_loss:0.15747
epoch [382/1001], MSE_loss:0.18755
epoch [383/1001], MSE_loss:0.12527
epoch [384/1001], MSE_loss:0.13257
epoch [385/1001], MSE_loss:0.12553
epoch [386/1001], MSE_loss:0.08324
epoch [387/1001], MSE_loss:0.12003
epoch [388/1001], MSE_loss:0.13997
epoch [389/1001], MSE_loss:0.08193
epoch [390/1001], MSE_loss:0.11289
epoch [391/1001], MSE_loss:0.13441
epoch [392/1001], MSE_loss:0.12930
epoch [393/1001], MSE_loss:0.12780
epoch [394/1001], MSE_loss:0.11533
epoch [395/1001], MSE_loss:0.13596
epoch [396/1001], MSE_loss:0.13465
epoch [397/1001], MSE_loss:0.10570
epoch [398/1001], MSE_loss:0.10952
epoch [399/1001], MSE_loss:0.09972
epoch [400/1001], MSE_loss:0.11198
epoch [401/1001], MSE_loss:0.12729
epoch [402/1001], MSE_loss:0.08678
epoch [403/1001], MSE_loss:0.13066
epoch [404/1001], MSE_loss:0.09720
epoch [405/1001], MSE_loss:0.12190
epoch [406/1001], MSE_loss:0.12027
epoch [407/1001], MSE_loss:0.10794
epoch [408/1001], MSE_loss:0.13370
epoch [409/1001], MSE_loss:0.12164
epoch [410/1001], MSE_loss:0.14211
epoch [411/1001], MSE_loss:0.14047
epoch [412/1001], MSE_loss:0.09075
epoch [413/1001], MSE_loss:0.13676
epoch [414/1001], MSE_loss:0.14556
epoch [415/1001], MSE_loss:0.11188
epoch [416/1001], MSE_loss:0.11907
epoch [417/1001], MSE_loss:0.11887
epoch [418/1001], MSE_loss:0.12069
epoch [419/1001], MSE_loss:0.11633
epoch [420/1001], MSE_loss:0.11093
epoch [421/1001], MSE_loss:0.15718
epoch [422/1001], MSE_loss:0.08233
epoch [423/1001], MSE_loss:0.13869
epoch [424/1001], MSE_loss:0.11318
epoch [425/1001], MSE_loss:0.12721
epoch [426/1001], MSE_loss:0.11380
epoch [427/1001], MSE_loss:0.11083
epoch [428/1001], MSE_loss:0.13312
epoch [429/1001], MSE_loss:0.11241
epoch [430/1001], MSE_loss:0.10951
epoch [431/1001], MSE_loss:0.12817
epoch [432/1001], MSE_loss:0.08485
epoch [433/1001], MSE_loss:0.11636
epoch [434/1001], MSE_loss:0.15320
epoch [435/1001], MSE_loss:0.11487
epoch [436/1001], MSE_loss:0.08831
epoch [437/1001], MSE_loss:0.10175
epoch [438/1001], MSE_loss:0.09676
epoch [439/1001], MSE_loss:0.13603
epoch [440/1001], MSE_loss:0.10804
epoch [441/1001], MSE_loss:0.14970
epoch [442/1001], MSE_loss:0.11937
epoch [443/1001], MSE_loss:0.08311
epoch [444/1001], MSE_loss:0.15206
epoch [445/1001], MSE_loss:0.13178
epoch [446/1001], MSE_loss:0.11516
epoch [447/1001], MSE_loss:0.08963
epoch [448/1001], MSE_loss:0.10535
epoch [449/1001], MSE_loss:0.08424
epoch [450/1001], MSE_loss:0.10085
epoch [451/1001], MSE_loss:0.10693
epoch [452/1001], MSE_loss:0.14066
epoch [453/1001], MSE_loss:0.12306
epoch [454/1001], MSE_loss:0.11153
epoch [455/1001], MSE_loss:0.11173
epoch [456/1001], MSE_loss:0.10971
epoch [457/1001], MSE_loss:0.10989
epoch [458/1001], MSE_loss:0.12295
epoch [459/1001], MSE_loss:0.11160
epoch [460/1001], MSE_loss:0.11701
epoch [461/1001], MSE_loss:0.10271
epoch [462/1001], MSE_loss:0.10061
epoch [463/1001], MSE_loss:0.13303
epoch [464/1001], MSE_loss:0.12347
epoch [465/1001], MSE_loss:0.10158
epoch [466/1001], MSE_loss:0.10424
epoch [467/1001], MSE_loss:0.12392
epoch [468/1001], MSE_loss:0.10983
epoch [469/1001], MSE_loss:0.09256
epoch [470/1001], MSE_loss:0.09455
epoch [471/1001], MSE_loss:0.08862
epoch [472/1001], MSE_loss:0.13935
epoch [473/1001], MSE_loss:0.13739
epoch [474/1001], MSE_loss:0.15079
epoch [475/1001], MSE_loss:0.07853
epoch [476/1001], MSE_loss:0.09233
epoch [477/1001], MSE_loss:0.13673
epoch [478/1001], MSE_loss:0.12149
epoch [479/1001], MSE_loss:0.12467
epoch [480/1001], MSE_loss:0.11458
epoch [481/1001], MSE_loss:0.12036
epoch [482/1001], MSE_loss:0.14412
epoch [483/1001], MSE_loss:0.10073
epoch [484/1001], MSE_loss:0.13366
epoch [485/1001], MSE_loss:0.10479
epoch [486/1001], MSE_loss:0.14265
epoch [487/1001], MSE_loss:0.07575
epoch [488/1001], MSE_loss:0.11490
epoch [489/1001], MSE_loss:0.11777
epoch [490/1001], MSE_loss:0.13915
epoch [491/1001], MSE_loss:0.11169
epoch [492/1001], MSE_loss:0.11954
epoch [493/1001], MSE_loss:0.12219
epoch [494/1001], MSE_loss:0.16133
epoch [495/1001], MSE_loss:0.17075
epoch [496/1001], MSE_loss:0.09640
epoch [497/1001], MSE_loss:0.09853
epoch [498/1001], MSE_loss:0.13440
epoch [499/1001], MSE_loss:0.13067
epoch [500/1001], MSE_loss:0.12189
epoch [501/1001], MSE_loss:0.12978
epoch [502/1001], MSE_loss:0.10572
epoch [503/1001], MSE_loss:0.13539
epoch [504/1001], MSE_loss:0.13013
epoch [505/1001], MSE_loss:0.13832
epoch [506/1001], MSE_loss:0.11567
epoch [507/1001], MSE_loss:0.13159
epoch [508/1001], MSE_loss:0.09669
epoch [509/1001], MSE_loss:0.08700
epoch [510/1001], MSE_loss:0.12316
epoch [511/1001], MSE_loss:0.19585
epoch [512/1001], MSE_loss:0.09869
epoch [513/1001], MSE_loss:0.09730
epoch [514/1001], MSE_loss:0.13185
epoch [515/1001], MSE_loss:0.13027
epoch [516/1001], MSE_loss:0.12452
epoch [517/1001], MSE_loss:0.10401
epoch [518/1001], MSE_loss:0.09578
epoch [519/1001], MSE_loss:0.11293
epoch [520/1001], MSE_loss:0.09747
epoch [521/1001], MSE_loss:0.10950
epoch [522/1001], MSE_loss:0.15282
epoch [523/1001], MSE_loss:0.08326
epoch [524/1001], MSE_loss:0.09864
epoch [525/1001], MSE_loss:0.11189
epoch [526/1001], MSE_loss:0.10523
epoch [527/1001], MSE_loss:0.16056
epoch [528/1001], MSE_loss:0.10593
epoch [529/1001], MSE_loss:0.10436
epoch [530/1001], MSE_loss:0.11917
epoch [531/1001], MSE_loss:0.12997
epoch [532/1001], MSE_loss:0.07603
epoch [533/1001], MSE_loss:0.14818
epoch [534/1001], MSE_loss:0.15229
epoch [535/1001], MSE_loss:0.14909
epoch [536/1001], MSE_loss:0.12504
epoch [537/1001], MSE_loss:0.11090
epoch [538/1001], MSE_loss:0.12928
epoch [539/1001], MSE_loss:0.08096
epoch [540/1001], MSE_loss:0.10194
epoch [541/1001], MSE_loss:0.13395
epoch [542/1001], MSE_loss:0.10084
epoch [543/1001], MSE_loss:0.10713
epoch [544/1001], MSE_loss:0.09193
epoch [545/1001], MSE_loss:0.14952
epoch [546/1001], MSE_loss:0.18350
epoch [547/1001], MSE_loss:0.13066
epoch [548/1001], MSE_loss:0.12798
epoch [549/1001], MSE_loss:0.15369
epoch [550/1001], MSE_loss:0.10805
epoch [551/1001], MSE_loss:0.10022
epoch [552/1001], MSE_loss:0.16764
epoch [553/1001], MSE_loss:0.13253
epoch [554/1001], MSE_loss:0.12520
epoch [555/1001], MSE_loss:0.11622
epoch [556/1001], MSE_loss:0.12741
epoch [557/1001], MSE_loss:0.10768
epoch [558/1001], MSE_loss:0.13022
epoch [559/1001], MSE_loss:0.10317
epoch [560/1001], MSE_loss:0.14954
epoch [561/1001], MSE_loss:0.12225
epoch [562/1001], MSE_loss:0.09520
epoch [563/1001], MSE_loss:0.09120
epoch [564/1001], MSE_loss:0.11296
epoch [565/1001], MSE_loss:0.08315
epoch [566/1001], MSE_loss:0.09164
epoch [567/1001], MSE_loss:0.14568
epoch [568/1001], MSE_loss:0.10894
epoch [569/1001], MSE_loss:0.10126
epoch [570/1001], MSE_loss:0.12017
epoch [571/1001], MSE_loss:0.12887
epoch [572/1001], MSE_loss:0.14425
epoch [573/1001], MSE_loss:0.10877
epoch [574/1001], MSE_loss:0.11539
epoch [575/1001], MSE_loss:0.10568
epoch [576/1001], MSE_loss:0.12358
epoch [577/1001], MSE_loss:0.12561
epoch [578/1001], MSE_loss:0.09799
epoch [579/1001], MSE_loss:0.10842
epoch [580/1001], MSE_loss:0.11411
epoch [581/1001], MSE_loss:0.09202
epoch [582/1001], MSE_loss:0.12320
epoch [583/1001], MSE_loss:0.09529
epoch [584/1001], MSE_loss:0.11868
epoch [585/1001], MSE_loss:0.11457
epoch [586/1001], MSE_loss:0.14450
epoch [587/1001], MSE_loss:0.10678
epoch [588/1001], MSE_loss:0.14179
epoch [589/1001], MSE_loss:0.15383
epoch [590/1001], MSE_loss:0.11393
epoch [591/1001], MSE_loss:0.13608
epoch [592/1001], MSE_loss:0.11964
epoch [593/1001], MSE_loss:0.10641
epoch [594/1001], MSE_loss:0.12335
epoch [595/1001], MSE_loss:0.11648
epoch [596/1001], MSE_loss:0.08500
epoch [597/1001], MSE_loss:0.12124
epoch [598/1001], MSE_loss:0.17018
epoch [599/1001], MSE_loss:0.12200
epoch [600/1001], MSE_loss:0.13461
epoch [601/1001], MSE_loss:0.13053
epoch [602/1001], MSE_loss:0.10891
epoch [603/1001], MSE_loss:0.13075
epoch [604/1001], MSE_loss:0.09031
epoch [605/1001], MSE_loss:0.12766
epoch [606/1001], MSE_loss:0.10927
epoch [607/1001], MSE_loss:0.12586
epoch [608/1001], MSE_loss:0.11106
epoch [609/1001], MSE_loss:0.09347
epoch [610/1001], MSE_loss:0.10514
epoch [611/1001], MSE_loss:0.13271
epoch [612/1001], MSE_loss:0.12595
epoch [613/1001], MSE_loss:0.11086
epoch [614/1001], MSE_loss:0.08209
epoch [615/1001], MSE_loss:0.11750
epoch [616/1001], MSE_loss:0.13321
epoch [617/1001], MSE_loss:0.11788
epoch [618/1001], MSE_loss:0.16106
epoch [619/1001], MSE_loss:0.12809
epoch [620/1001], MSE_loss:0.07791
epoch [621/1001], MSE_loss:0.14732
epoch [622/1001], MSE_loss:0.13433
epoch [623/1001], MSE_loss:0.10761
epoch [624/1001], MSE_loss:0.19539
epoch [625/1001], MSE_loss:0.13428
epoch [626/1001], MSE_loss:0.10177
epoch [627/1001], MSE_loss:0.14641
epoch [628/1001], MSE_loss:0.09773
epoch [629/1001], MSE_loss:0.11281
epoch [630/1001], MSE_loss:0.12041
epoch [631/1001], MSE_loss:0.18124
epoch [632/1001], MSE_loss:0.10296
epoch [633/1001], MSE_loss:0.13991
epoch [634/1001], MSE_loss:0.11006
epoch [635/1001], MSE_loss:0.12588
epoch [636/1001], MSE_loss:0.11280
epoch [637/1001], MSE_loss:0.17101
epoch [638/1001], MSE_loss:0.10777
epoch [639/1001], MSE_loss:0.07476
epoch [640/1001], MSE_loss:0.10252
epoch [641/1001], MSE_loss:0.07057
epoch [642/1001], MSE_loss:0.10328
epoch [643/1001], MSE_loss:0.14175
epoch [644/1001], MSE_loss:0.11096
epoch [645/1001], MSE_loss:0.11129
epoch [646/1001], MSE_loss:0.16014
epoch [647/1001], MSE_loss:0.07444
epoch [648/1001], MSE_loss:0.14728
epoch [649/1001], MSE_loss:0.07371
epoch [650/1001], MSE_loss:0.08594
epoch [651/1001], MSE_loss:0.12174
epoch [652/1001], MSE_loss:0.10133
epoch [653/1001], MSE_loss:0.09449
epoch [654/1001], MSE_loss:0.10919
epoch [655/1001], MSE_loss:0.12055
epoch [656/1001], MSE_loss:0.13395
epoch [657/1001], MSE_loss:0.08308
epoch [658/1001], MSE_loss:0.09790
epoch [659/1001], MSE_loss:0.14518
epoch [660/1001], MSE_loss:0.13484
epoch [661/1001], MSE_loss:0.09939
epoch [662/1001], MSE_loss:0.11926
epoch [663/1001], MSE_loss:0.09847
epoch [664/1001], MSE_loss:0.12467
epoch [665/1001], MSE_loss:0.12239
epoch [666/1001], MSE_loss:0.10457
epoch [667/1001], MSE_loss:0.12985
epoch [668/1001], MSE_loss:0.09404
epoch [669/1001], MSE_loss:0.12474
epoch [670/1001], MSE_loss:0.09235
epoch [671/1001], MSE_loss:0.16718
epoch [672/1001], MSE_loss:0.12698
epoch [673/1001], MSE_loss:0.11982
epoch [674/1001], MSE_loss:0.09609
epoch [675/1001], MSE_loss:0.10359
epoch [676/1001], MSE_loss:0.11158
epoch [677/1001], MSE_loss:0.10206
epoch [678/1001], MSE_loss:0.09306
epoch [679/1001], MSE_loss:0.14665
epoch [680/1001], MSE_loss:0.10462
epoch [681/1001], MSE_loss:0.11560
epoch [682/1001], MSE_loss:0.08974
epoch [683/1001], MSE_loss:0.12469
epoch [684/1001], MSE_loss:0.13628
epoch [685/1001], MSE_loss:0.09854
epoch [686/1001], MSE_loss:0.10269
epoch [687/1001], MSE_loss:0.11850
epoch [688/1001], MSE_loss:0.08046
epoch [689/1001], MSE_loss:0.07754
epoch [690/1001], MSE_loss:0.09215
epoch [691/1001], MSE_loss:0.12361
epoch [692/1001], MSE_loss:0.09991
epoch [693/1001], MSE_loss:0.08718
epoch [694/1001], MSE_loss:0.11392
epoch [695/1001], MSE_loss:0.09510
epoch [696/1001], MSE_loss:0.11473
epoch [697/1001], MSE_loss:0.09638
epoch [698/1001], MSE_loss:0.13156
epoch [699/1001], MSE_loss:0.09052
epoch [700/1001], MSE_loss:0.10374
epoch [701/1001], MSE_loss:0.10737
epoch [702/1001], MSE_loss:0.11530
epoch [703/1001], MSE_loss:0.09188
epoch [704/1001], MSE_loss:0.12018
epoch [705/1001], MSE_loss:0.10628
epoch [706/1001], MSE_loss:0.08592
epoch [707/1001], MSE_loss:0.09723
epoch [708/1001], MSE_loss:0.14817
epoch [709/1001], MSE_loss:0.07180
epoch [710/1001], MSE_loss:0.08186
epoch [711/1001], MSE_loss:0.13158
epoch [712/1001], MSE_loss:0.12748
epoch [713/1001], MSE_loss:0.10338
epoch [714/1001], MSE_loss:0.13063
epoch [715/1001], MSE_loss:0.13040
epoch [716/1001], MSE_loss:0.11914
epoch [717/1001], MSE_loss:0.11606
epoch [718/1001], MSE_loss:0.10733
epoch [719/1001], MSE_loss:0.14393
epoch [720/1001], MSE_loss:0.12749
epoch [721/1001], MSE_loss:0.15856
epoch [722/1001], MSE_loss:0.16495
epoch [723/1001], MSE_loss:0.09334
epoch [724/1001], MSE_loss:0.14640
epoch [725/1001], MSE_loss:0.11028
epoch [726/1001], MSE_loss:0.08888
epoch [727/1001], MSE_loss:0.07562
epoch [728/1001], MSE_loss:0.13480
epoch [729/1001], MSE_loss:0.16069
epoch [730/1001], MSE_loss:0.14847
epoch [731/1001], MSE_loss:0.10919
epoch [732/1001], MSE_loss:0.09002
epoch [733/1001], MSE_loss:0.13155
epoch [734/1001], MSE_loss:0.13003
epoch [735/1001], MSE_loss:0.14722
epoch [736/1001], MSE_loss:0.14622
epoch [737/1001], MSE_loss:0.10726
epoch [738/1001], MSE_loss:0.06945
epoch [739/1001], MSE_loss:0.09805
epoch [740/1001], MSE_loss:0.09107
epoch [741/1001], MSE_loss:0.17342
epoch [742/1001], MSE_loss:0.11860
epoch [743/1001], MSE_loss:0.14453
epoch [744/1001], MSE_loss:0.11367
epoch [745/1001], MSE_loss:0.13167
epoch [746/1001], MSE_loss:0.08406
epoch [747/1001], MSE_loss:0.08840
epoch [748/1001], MSE_loss:0.08526
epoch [749/1001], MSE_loss:0.12368
epoch [750/1001], MSE_loss:0.07045
epoch [751/1001], MSE_loss:0.09448
epoch [752/1001], MSE_loss:0.14658
epoch [753/1001], MSE_loss:0.18945
epoch [754/1001], MSE_loss:0.13863
epoch [755/1001], MSE_loss:0.10304
epoch [756/1001], MSE_loss:0.13800
epoch [757/1001], MSE_loss:0.10768
epoch [758/1001], MSE_loss:0.10706
epoch [759/1001], MSE_loss:0.11364
epoch [760/1001], MSE_loss:0.09974
epoch [761/1001], MSE_loss:0.11742
epoch [762/1001], MSE_loss:0.09856
epoch [763/1001], MSE_loss:0.11827
epoch [764/1001], MSE_loss:0.07610
epoch [765/1001], MSE_loss:0.12082
epoch [766/1001], MSE_loss:0.12524
epoch [767/1001], MSE_loss:0.14168
epoch [768/1001], MSE_loss:0.10628
epoch [769/1001], MSE_loss:0.12140
epoch [770/1001], MSE_loss:0.09698
epoch [771/1001], MSE_loss:0.09453
epoch [772/1001], MSE_loss:0.12233
epoch [773/1001], MSE_loss:0.14065
epoch [774/1001], MSE_loss:0.10812
epoch [775/1001], MSE_loss:0.11873
epoch [776/1001], MSE_loss:0.07767
epoch [777/1001], MSE_loss:0.11603
epoch [778/1001], MSE_loss:0.14670
epoch [779/1001], MSE_loss:0.13087
epoch [780/1001], MSE_loss:0.16548
epoch [781/1001], MSE_loss:0.10457
epoch [782/1001], MSE_loss:0.09638
epoch [783/1001], MSE_loss:0.15248
epoch [784/1001], MSE_loss:0.13468
epoch [785/1001], MSE_loss:0.11529
epoch [786/1001], MSE_loss:0.08815
epoch [787/1001], MSE_loss:0.09667
epoch [788/1001], MSE_loss:0.11397
epoch [789/1001], MSE_loss:0.08605
epoch [790/1001], MSE_loss:0.10968
epoch [791/1001], MSE_loss:0.10595
epoch [792/1001], MSE_loss:0.12051
epoch [793/1001], MSE_loss:0.14003
epoch [794/1001], MSE_loss:0.09195
epoch [795/1001], MSE_loss:0.12857
epoch [796/1001], MSE_loss:0.09116
epoch [797/1001], MSE_loss:0.09032
epoch [798/1001], MSE_loss:0.11371
epoch [799/1001], MSE_loss:0.09659
epoch [800/1001], MSE_loss:0.14991
epoch [801/1001], MSE_loss:0.15674
epoch [802/1001], MSE_loss:0.10257
epoch [803/1001], MSE_loss:0.12772
epoch [804/1001], MSE_loss:0.14534
epoch [805/1001], MSE_loss:0.13016
epoch [806/1001], MSE_loss:0.12885
epoch [807/1001], MSE_loss:0.09811
epoch [808/1001], MSE_loss:0.07403
epoch [809/1001], MSE_loss:0.14038
epoch [810/1001], MSE_loss:0.12609
epoch [811/1001], MSE_loss:0.09554
epoch [812/1001], MSE_loss:0.12714
epoch [813/1001], MSE_loss:0.10192
epoch [814/1001], MSE_loss:0.09782
epoch [815/1001], MSE_loss:0.11600
epoch [816/1001], MSE_loss:0.15215
epoch [817/1001], MSE_loss:0.11896
epoch [818/1001], MSE_loss:0.10352
epoch [819/1001], MSE_loss:0.13054
epoch [820/1001], MSE_loss:0.15424
epoch [821/1001], MSE_loss:0.11149
epoch [822/1001], MSE_loss:0.10535
epoch [823/1001], MSE_loss:0.16022
epoch [824/1001], MSE_loss:0.14428
epoch [825/1001], MSE_loss:0.12556
epoch [826/1001], MSE_loss:0.09748
epoch [827/1001], MSE_loss:0.11627
epoch [828/1001], MSE_loss:0.14174
epoch [829/1001], MSE_loss:0.13296
epoch [830/1001], MSE_loss:0.11462
epoch [831/1001], MSE_loss:0.10776
epoch [832/1001], MSE_loss:0.12590
epoch [833/1001], MSE_loss:0.10329
epoch [834/1001], MSE_loss:0.07105
epoch [835/1001], MSE_loss:0.12542
epoch [836/1001], MSE_loss:0.09219
epoch [837/1001], MSE_loss:0.14856
epoch [838/1001], MSE_loss:0.11689
epoch [839/1001], MSE_loss:0.13348
epoch [840/1001], MSE_loss:0.07701
epoch [841/1001], MSE_loss:0.08899
epoch [842/1001], MSE_loss:0.13608
epoch [843/1001], MSE_loss:0.10408
epoch [844/1001], MSE_loss:0.09543
epoch [845/1001], MSE_loss:0.09831
epoch [846/1001], MSE_loss:0.12091
epoch [847/1001], MSE_loss:0.12162
epoch [848/1001], MSE_loss:0.14679
epoch [849/1001], MSE_loss:0.13002
epoch [850/1001], MSE_loss:0.13717
epoch [851/1001], MSE_loss:0.10268
epoch [852/1001], MSE_loss:0.11947
epoch [853/1001], MSE_loss:0.12431
epoch [854/1001], MSE_loss:0.11111
epoch [855/1001], MSE_loss:0.10501
epoch [856/1001], MSE_loss:0.11640
epoch [857/1001], MSE_loss:0.15649
epoch [858/1001], MSE_loss:0.14032
epoch [859/1001], MSE_loss:0.10284
epoch [860/1001], MSE_loss:0.09295
epoch [861/1001], MSE_loss:0.11751
epoch [862/1001], MSE_loss:0.10114
epoch [863/1001], MSE_loss:0.13018
epoch [864/1001], MSE_loss:0.14826
epoch [865/1001], MSE_loss:0.13769
epoch [866/1001], MSE_loss:0.15459
epoch [867/1001], MSE_loss:0.14331
epoch [868/1001], MSE_loss:0.11248
epoch [869/1001], MSE_loss:0.13260
epoch [870/1001], MSE_loss:0.17195
epoch [871/1001], MSE_loss:0.09647
epoch [872/1001], MSE_loss:0.12371
epoch [873/1001], MSE_loss:0.11903
epoch [874/1001], MSE_loss:0.08869
epoch [875/1001], MSE_loss:0.12191
epoch [876/1001], MSE_loss:0.10686
epoch [877/1001], MSE_loss:0.11671
epoch [878/1001], MSE_loss:0.09522
epoch [879/1001], MSE_loss:0.11735
epoch [880/1001], MSE_loss:0.08739
epoch [881/1001], MSE_loss:0.12170
epoch [882/1001], MSE_loss:0.11346
epoch [883/1001], MSE_loss:0.11568
epoch [884/1001], MSE_loss:0.09871
epoch [885/1001], MSE_loss:0.10188
epoch [886/1001], MSE_loss:0.15466
epoch [887/1001], MSE_loss:0.10640
epoch [888/1001], MSE_loss:0.14131
epoch [889/1001], MSE_loss:0.17345
epoch [890/1001], MSE_loss:0.08667
epoch [891/1001], MSE_loss:0.12750
epoch [892/1001], MSE_loss:0.12401
epoch [893/1001], MSE_loss:0.12210
epoch [894/1001], MSE_loss:0.13786
epoch [895/1001], MSE_loss:0.13137
epoch [896/1001], MSE_loss:0.15604
epoch [897/1001], MSE_loss:0.11150
epoch [898/1001], MSE_loss:0.13177
epoch [899/1001], MSE_loss:0.11160
epoch [900/1001], MSE_loss:0.14266
epoch [901/1001], MSE_loss:0.08484
epoch [902/1001], MSE_loss:0.11936
epoch [903/1001], MSE_loss:0.10940
epoch [904/1001], MSE_loss:0.10427
epoch [905/1001], MSE_loss:0.09522
epoch [906/1001], MSE_loss:0.10320
epoch [907/1001], MSE_loss:0.10156
epoch [908/1001], MSE_loss:0.12466
epoch [909/1001], MSE_loss:0.17056
epoch [910/1001], MSE_loss:0.12418
epoch [911/1001], MSE_loss:0.10719
epoch [912/1001], MSE_loss:0.11191
epoch [913/1001], MSE_loss:0.10774
epoch [914/1001], MSE_loss:0.15692
epoch [915/1001], MSE_loss:0.12649
epoch [916/1001], MSE_loss:0.12595
epoch [917/1001], MSE_loss:0.12102
epoch [918/1001], MSE_loss:0.10165
epoch [919/1001], MSE_loss:0.08080
epoch [920/1001], MSE_loss:0.12277
epoch [921/1001], MSE_loss:0.15367
epoch [922/1001], MSE_loss:0.11200
epoch [923/1001], MSE_loss:0.11082
epoch [924/1001], MSE_loss:0.12726
epoch [925/1001], MSE_loss:0.10856
epoch [926/1001], MSE_loss:0.12725
epoch [927/1001], MSE_loss:0.11456
epoch [928/1001], MSE_loss:0.13241
epoch [929/1001], MSE_loss:0.10733
epoch [930/1001], MSE_loss:0.12021
epoch [931/1001], MSE_loss:0.11019
epoch [932/1001], MSE_loss:0.12138
epoch [933/1001], MSE_loss:0.10091
epoch [934/1001], MSE_loss:0.13850
epoch [935/1001], MSE_loss:0.14093
epoch [936/1001], MSE_loss:0.16273
epoch [937/1001], MSE_loss:0.08786
epoch [938/1001], MSE_loss:0.13768
epoch [939/1001], MSE_loss:0.08799
epoch [940/1001], MSE_loss:0.07898
epoch [941/1001], MSE_loss:0.17626
epoch [942/1001], MSE_loss:0.11567
epoch [943/1001], MSE_loss:0.16509
epoch [944/1001], MSE_loss:0.12463
epoch [945/1001], MSE_loss:0.09495
epoch [946/1001], MSE_loss:0.11599
epoch [947/1001], MSE_loss:0.12557
epoch [948/1001], MSE_loss:0.08813
epoch [949/1001], MSE_loss:0.10419
epoch [950/1001], MSE_loss:0.11379
epoch [951/1001], MSE_loss:0.11961
epoch [952/1001], MSE_loss:0.11252
epoch [953/1001], MSE_loss:0.08131
epoch [954/1001], MSE_loss:0.07607
epoch [955/1001], MSE_loss:0.11238
epoch [956/1001], MSE_loss:0.11267
epoch [957/1001], MSE_loss:0.12717
epoch [958/1001], MSE_loss:0.12429
epoch [959/1001], MSE_loss:0.08829
epoch [960/1001], MSE_loss:0.09827
epoch [961/1001], MSE_loss:0.10128
epoch [962/1001], MSE_loss:0.12911
epoch [963/1001], MSE_loss:0.17698
epoch [964/1001], MSE_loss:0.10555
epoch [965/1001], MSE_loss:0.09032
epoch [966/1001], MSE_loss:0.10359
epoch [967/1001], MSE_loss:0.18606
epoch [968/1001], MSE_loss:0.10108
epoch [969/1001], MSE_loss:0.09484
epoch [970/1001], MSE_loss:0.08249
epoch [971/1001], MSE_loss:0.11780
epoch [972/1001], MSE_loss:0.08996
epoch [973/1001], MSE_loss:0.12337
epoch [974/1001], MSE_loss:0.13010
epoch [975/1001], MSE_loss:0.09174
epoch [976/1001], MSE_loss:0.11197
epoch [977/1001], MSE_loss:0.09415
epoch [978/1001], MSE_loss:0.11814
epoch [979/1001], MSE_loss:0.13093
epoch [980/1001], MSE_loss:0.12450
epoch [981/1001], MSE_loss:0.14128
epoch [982/1001], MSE_loss:0.12729
epoch [983/1001], MSE_loss:0.10449
epoch [984/1001], MSE_loss:0.10275
epoch [985/1001], MSE_loss:0.10237
epoch [986/1001], MSE_loss:0.12374
epoch [987/1001], MSE_loss:0.12286
epoch [988/1001], MSE_loss:0.10737
epoch [989/1001], MSE_loss:0.12439
epoch [990/1001], MSE_loss:0.09180
epoch [991/1001], MSE_loss:0.13252
epoch [992/1001], MSE_loss:0.13369
epoch [993/1001], MSE_loss:0.10747
epoch [994/1001], MSE_loss:0.14860
epoch [995/1001], MSE_loss:0.13668
epoch [996/1001], MSE_loss:0.10986
epoch [997/1001], MSE_loss:0.10133
epoch [998/1001], MSE_loss:0.10530
epoch [999/1001], MSE_loss:0.10785
epoch [1000/1001], MSE_loss:0.12613
epoch [1001/1001], MSE_loss:0.11618

input_data_device = input_data.to(device)

latent_features = autoencoder.encode(input_data_device).detach().cpu().numpy()

print(latent_features.shape)

(360, 16)

tsne = TSNE(n_components=2, init='pca', random_state=0, n_jobs=-1, perplexity=30)

tsne_2d = tsne.fit_transform(latent_features)

fig, axi1=plt.subplots(1, figsize=(2, 1.5))
axi1.scatter(tsne_2d[:, 0], tsne_2d[:, 1],
            marker='*', s=10, color=sns.color_palette('Paired')[1],
            )

ax = plt.gca()
plt.grid(True, linewidth=0.5, color='gray', linestyle=':')
plt.xlim([-30, 30])
plt.ylim([-30, 30])
# plt.yticks([-100,-50,0,50,100],[-100,-50,0,50,100])
# plt.xticks([-100,-50,0,50,100],[-100,-50,0,50,100])

ax.tick_params(which='both', bottom=True, top=False, left=True, right=False,
            labelbottom=True, labelleft=True, direction='out',width=1)
plt.show()

tmp = copy.deepcopy(input_data_raw)

np.random.shuffle(tmp)
np.random.shuffle(tmp)

data_shuffle = torch.from_numpy(tmp).type(torch.FloatTensor)

importlib.reload(UDEC_Network)

<module 'utils.UDEC_Network' from 'e:\\论文写作\\论文2\\N170\\utils\\UDEC_Network.py'>

EPOCHS = 10001
BATCH_SIZE = 512
lr = 0.6
file_path_prefix = './network_data/'

for ind, n_c in enumerate([8, 10, 12]):

    autoencoder = UDEC_Network.AutoEncoder().to(device)
    ae_save_path = file_path_prefix + 'autoencoder.pth'
    checkpoint = torch.load(ae_save_path)
    autoencoder.load_state_dict(checkpoint['state_dict'])

    dec = UDEC_Network.DEC(n_clusters=n_c, autoencoder=autoencoder, hidden=16, cluster_centers=None, alpha=2.0).to(device)

    dec_save_path = file_path_prefix + 'dec-' + str(n_c) + '-clusters' + '.pth'
    checkpoint = { "epoch": 0, "best": float("inf") }
    UDEC_Network.train(data=data_shuffle, model=dec, num_epochs=EPOCHS, 
                            n_cluster=n_c, draw_pic=True, lr=lr, file_path_prefix=file_path_prefix, 
                            savepath=dec_save_path, checkpoint=checkpoint, batch_size=BATCH_SIZE)

Training
plotting
Epochs: [0/10001] Loss:0.22805804014205933
Epochs: [1000/10001] Loss:0.005099236965179443
Epochs: [2000/10001] Loss:0.0034260167740285397
Epochs: [3000/10001] Loss:0.002703610109165311
Epochs: [4000/10001] Loss:0.0022824450861662626
plotting
Epochs: [5000/10001] Loss:0.0020003465469926596
Epochs: [6000/10001] Loss:0.001795316464267671
Epochs: [7000/10001] Loss:0.001638207584619522
Epochs: [8000/10001] Loss:0.001513019553385675
Epochs: [9000/10001] Loss:0.0014104674337431788
plotting
Epochs: [10000/10001] Loss:0.0013245934387668967
Training
plotting
Epochs: [0/10001] Loss:0.2488413155078888
Epochs: [1000/10001] Loss:0.00670035183429718
Epochs: [2000/10001] Loss:0.0044983853586018085
Epochs: [3000/10001] Loss:0.003548107575625181
Epochs: [4000/10001] Loss:0.0029942328110337257
plotting
Epochs: [5000/10001] Loss:0.002623306354507804
Epochs: [6000/10001] Loss:0.0023538924288004637
Epochs: [7000/10001] Loss:0.0021474051754921675
Epochs: [8000/10001] Loss:0.001982996938750148
Epochs: [9000/10001] Loss:0.0018482827581465244
plotting
Epochs: [10000/10001] Loss:0.0017354899318888783
Training
plotting
Epochs: [0/10001] Loss:0.27088484168052673
Epochs: [1000/10001] Loss:0.008441154845058918
Epochs: [2000/10001] Loss:0.0056488607078790665
Epochs: [3000/10001] Loss:0.0044504995457828045
Epochs: [4000/10001] Loss:0.0037538264878094196
plotting
Epochs: [5000/10001] Loss:0.0032879486680030823
Epochs: [6000/10001] Loss:0.0029497873038053513
Epochs: [7000/10001] Loss:0.002690780209377408
Epochs: [8000/10001] Loss:0.002484602387994528
Epochs: [9000/10001] Loss:0.0023157692048698664
plotting
Epochs: [10000/10001] Loss:0.0021743634715676308

data = torch.from_numpy(input_data_raw).type(torch.FloatTensor)

num_clusters = [8,10,12]

latent_vec = np.empty( (len(num_clusters), data.size()[0], 16) )  # [n_c, frames, n_hidden]
pred_label = np.empty( (len(num_clusters), data.size()[0]) )
pred_center = []

file_path_prefix = './network_data/'
for ind, n_c in enumerate(num_clusters): 

    # load model
    autoencoder = UDEC_Network.AutoEncoder()

    dec = UDEC_Network.DEC(n_clusters=n_c, autoencoder=autoencoder, hidden=16, cluster_centers=None, alpha=2.0)
    dec_save_path = file_path_prefix + 'dec-' + str(n_c) + '-clusters' + '.pth'
    checkpoint = torch.load(dec_save_path)
    dec.load_state_dict(checkpoint['state_dict']);

    # calculate latent vectors
    latent_vec[ind] = autoencoder.encode(input_data).detach().cpu().numpy()

    # get cluster centers
    cluster = KMeans(n_clusters=num_clusters[ind], random_state=0, n_init=10*num_clusters[ind]).fit(latent_vec[ind])

    # get cluster labels
    centroid = cluster.cluster_centers_
    pred_center.append(centroid)
    pred_label[ind] = cluster.labels_ 

pred_label += 1

# with open('./tmp_data/eeg_data_udec_clustering_results.pkl', 'wb') as f:
#     dill.dump([pred_center, pred_label, centroid, latent_vec], f)

with open('./tmp_data/eeg_data_udec_clustering_results.pkl', 'rb') as f:
    [pred_center, pred_label, centroid, latent_vec] = dill.load(f)

tsne = TSNE(n_components=2, init='pca', random_state=0, n_jobs=-1, perplexity=30)

colors = sns.color_palette('pastel')

for ind, n_c in enumerate(num_clusters): 

    lf_with_center = np.vstack((latent_vec[ind], pred_center[ind]))

    kmeans_2d_with_center = tsne.fit_transform(lf_with_center)    
    kmeans_2d = kmeans_2d_with_center[:-n_c, :]
    kmeans_2d_center = kmeans_2d_with_center[-n_c:, :]

    fig, axi1=plt.subplots(1, figsize=(2, 1.5))    
    for i in range(n_c):
        axi1.scatter( kmeans_2d[pred_label[ind] == i+1, 0], 
                      kmeans_2d[pred_label[ind] == i+1, 1],
                      marker='*',
                      s=10,
                      color=plt.cm.tab20(i%20),
                    )
        axi1.text(kmeans_2d_center[i,0], kmeans_2d_center[i,1], 
                  i+1, fontsize=9, fontweight='semibold', 
                  verticalalignment='center', horizontalalignment='center', 
                  color='black', 
                )

    ax = plt.gca()
    plt.grid(True, linewidth=0.5, color='gray', linestyle=':')
    plt.xlim([-40, 40])
    plt.ylim([-40, 40])
    # plt.yticks([-100,-50,0,50,100],[-100,-50,0,50,100])
    # plt.xticks([-100,-50,0,50,100],[-100,-50,0,50,100])

    ax.tick_params(which='both', bottom=True, top=False, left=True, right=False,
                labelbottom=True, labelleft=True, direction='out',width=1)
    plt.show()

euc_center_index = []
rie_center_index = []

num_clusters = [8,10,12]

riemann_dist_symmetry = np.zeros_like(cov_dist_s)
for i in range(cov_dist_s.shape[0]):
    for j in range(i+1, cov_dist_s.shape[0]):
        riemann_dist_symmetry[i,j] = cov_dist_s[i,j]
        riemann_dist_symmetry[j,i] = cov_dist_s[i,j]

# Euclidean distance of lantent vectors
for i, n_c in enumerate(num_clusters):
    tmp_c = []
    for n in range(n_c):
        distance = np.sum(np.square(latent_vec[i][pred_label[i]==(n+1)] - pred_center[i][n]), axis=1)
        index = distance.argmin()
        tmp_c.append( np.argwhere(pred_label[i]==(n+1))[index][0] )
    euc_center_index.append(tmp_c)

# Riemann distance
for i, n_c in enumerate(num_clusters):
    tmp_c = []
    for n in range(n_c):

        tmp = riemann_dist_symmetry[pred_label[i]==(n+1), :]
        tmp2 = tmp[:, pred_label[i]==(n+1)]
        distance = np.sum(tmp2, axis=0)

        index = distance.argmin()
        tmp_c.append( np.argwhere(pred_label[i]==(n+1))[index][0] )
    rie_center_index.append(tmp_c)

print(euc_center_index[1])

print(rie_center_index[1])

[203, 269, 232, 133, 309, 298, 242, 89, 146, 182]
[207, 352, 50, 120, 323, 287, 256, 89, 156, 188]

clu_index = 0 # 8 clusters

cog_condition = [] # 2 conditions
time_index = [] # 0-180 time window

for ci in rie_center_index[clu_index]:
    cog_condition.append( 1+int(ci/180) )
    time_index.append( ci%180 )

print(cog_condition)
print(time_index)

[2, 2, 2, 1, 1, 2, 2, 2]
[26, 143, 88, 120, 53, 75, 56, 107]

import importlib
importlib.reload(ttest_for_clusters)

for n_c in range(len(num_clusters)):
    p_res = ttest_for_clusters.distance_ttest(pred_label[n_c], cov_dist_s, samp_num=500)
    ttest_for_clusters.draw_test_mat(p_res, corr_p=True)

[]

[]

[]

cluster_number_index = 0 # 8 clusters

each_condition_label = np.full((2, 180), np.nan)

type_num = 2
for tp in range(type_num):
    st = tp*180
    ed = st+180
    
    each_condition_label[tp] = pred_label[cluster_number_index, st:ed]

each_condition_label[1][9:12] = 1

for sym in range(type_num):
    draw_states.draw_state_blocks_for_eeg(each_condition_label[sym], figsize=(3.5, 1.0), n_clusters=8,
                                          #  n_clusters=int(np.max(each_condition_label[sym])),
                                          colorbar_fraction=0.015, tmin=0.0, tmax=0.7, 
                                          colorbar_ticks=[1,4,8]);

importlib.reload(draw_states)

for sym in range(type_num):
    draw_states.draw_state_blocks_for_eeg(each_condition_label[sym], figsize=(3.5, 1.0), n_clusters=8,
                                          #  n_clusters=int(np.max(each_condition_label[sym])),
                                          colorbar_fraction=0.015, tmin=0.0, tmax=0.7, 
                                          colorbar_ticks=[1,4,8], rie_dist=cov_dist_s, current_cluster=sym);

# erp_data_mean [2, 28, 256]
half_win = 12
start_t = 51
end_t = 231
len_t = 180

eeg_state_centers = np.zeros((8, 28))

for i, cog_ind in enumerate(cog_condition):
    eeg_state_centers[i] = np.mean(erp_data_mean[cog_ind-1, :, ((time_index[i]+start_t)-half_win):((time_index[i]+start_t)+half_win)], axis=1)

draw_states.draw_grand_average_topo(eeg_state_centers, epo, cmap='bwr', draw_separate=True, colorbar=False);

draw_states.draw_topo_diff(eeg_state_centers[3,:]-eeg_state_centers[7,:], epo, title='State 4 - State 8', cmap='bwr');

draw_states.draw_topo_diff(eeg_state_centers[4,:]-eeg_state_centers[6,:], epo, title='State 5 - State 7', cmap='bwr');

draw_states.draw_topo_diff(eeg_state_centers[3,:]-eeg_state_centers[1,:], epo, title='State 4 - State 2', cmap='bwr');

draw_states.draw_topo_diff(eeg_state_centers[6,:]-eeg_state_centers[1,:], epo, title='State 7 - State 2', cmap='bwr');

draw_states.draw_topo_diff(eeg_state_centers[2,:]-eeg_state_centers[1,:], epo, title='State 3 - State 2', cmap='bwr');

Import packages¶

Load EEG data¶

Plot ERP¶

Calculate spatial covariance matrix¶

Plot covariance matrices¶

Calculate spatial pattern distance¶

distance in observation space¶

distance in source space¶

Multi-dimensional Scaling¶

Data normlization¶

Train AutoEncoder Network¶

latent features visualization¶

Train clustering network¶

K-Means clustering of latent features¶

T-SNE visualization¶

Find index of cluster centers¶

t-test of clustering results¶

Plot microstate series¶

Draw center EEG topomap¶